Brazil Enable AI

australia index.md
Raw file
  • Enable AI Experiences -- AI experiences on the ServiceNow AI Platform extend your workflows with AI-driven automation. Use generative AI skills, AI agents, and agentic workflows to automate multi-step tasks, surface relevant answers, and support self-service across your organization.
    • Getting started with AI -- Prepare your instance for AI by learning about the applications and roles involved, exploring the AI Admin Center, and evaluating your data and configuration readiness.
    • Establishing AI governance -- Define policies, assign roles, and configure guardrails for responsible AI deployment across your organization.
      • AI governance -- As organizations increasingly adopt AI to drive efficiency, innovation, and customer experience, AI governance becomes essential to ensure responsible use, regulatory compliance, and alignment with enterprise goals. The ServiceNow AI Platform provides a comprehensive governance framework through key roles and applications that work together to manage AI across its life cycle.
      • AI Control Tower -- Gain visibility into your organization's AI footprint, manage the lifecycle of AI investments, govern risk and compliance, and measure the business impact of AI with AI Control Tower.
        • Explore -- Learn how AI Control Tower provides centralized visibility and governance across your organization's AI portfolio, connecting strategic planning, asset discovery, monitoring, compliance, and value measurement in a single workspace.
          • AI portfolio overview -- Act on the AI governance work that matters most, review the state of your AI portfolio, and track the value your AI assets deliver on the Home page in AI Control Tower.
          • Activity Center -- Track and act on the governance work generated across AI Control Tower from a single workspace, including lifecycle tasks, security tasks, change and offboarding requests, and AI recommendations.
          • Recommendations and AI insights -- Recommendations and AI insights direct your attention to the AI governance work that matters most, so you can resolve high-impact issues without searching for them.
          • ServiceNow Otto in AI Control Tower -- Ask questions about your AI portfolio in plain language and get answers drawn from your own AI Control Tower records.
        • Configure -- Set up AI Control Tower so your organization can begin managing AI assets, enforcing governance policies, and tracking AI value.
          • Activating AI Control Tower -- Govern, secure, and measure the value of your AI assets across the enterprise by activating AI Control Tower.
          • Guided setup -- Configure AI Control Tower in a logical sequence and track your progress from a single summary page, instead of navigating separate Settings pages.
            • Access guided setup -- Configure AI Control Tower in a logical sequence and track your progress toward a complete setup.
            • Guided setup areas -- Area-by-area listing of the setup items in guided setup, with cross-references to the topic each item relates to.
          • Configure users and roles -- Add and manage role to a user group to grant its members the corresponding permissions in AI Control Tower.
          • Configuring integrations -- Connect AI Control Tower to external AI platforms so you can discover AI assets, collect trace data for monitoring, and synchronize governance across multiple ServiceNow instances.
            • Configuring connectors -- Discover AI assets running on external platforms and hyperscaler environments to populate your AI asset inventory, apply consistent governance, and report on usage in AI Control Tower.
              • Create an AI connection for discovery -- Bring AI assets from an external platform into your AI asset inventory by creating an AI connection. AI Control Tower authenticates to the platform using your credentials and imports assets on a schedule, so they're governed and monitored alongside AI systems built natively on ServiceNow.
              • Create an AI connection for Veza access intelligence -- Connect AI Control Tower to Veza using OAuth 2.0 so that agent risk scores and severity levels from Veza access intelligence appear in the agent map. Since Veza is an enrichment connector, it doesn't import new assets.
            • Configuring trace connections -- Collect trace data from AI agents running on supported cloud platforms and monitoring services to generate evaluation metrics, populate AI inventory, and support security monitoring in AI Control Tower.
              • Add an AWS CloudWatch trace connection -- Monitor AI agents built with AWS Bedrock AgentCore by adding an AWS CloudWatch trace connection. AI Control Tower collects trace data through your AWS credentials and a MID Server, without requiring SDK instrumentation.
              • Add an Azure trace connection -- Monitor AI agents running on Microsoft Azure by adding an Azure trace connection. AI Control Tower collects trace data through your Azure credentials and a MID Server, without requiring SDK instrumentation.
              • Add a GCP Cloud Trace connection -- Monitor AI agents running on Google Cloud by adding a GCP Cloud Trace connection. AI Control Tower collects trace data through your Google Cloud credentials and a MID Server, without requiring SDK instrumentation.
              • Troubleshoot a trace connection -- Identify why a trace connection is not collecting data by reviewing its execution log and error messages.
              • Edit a trace connection -- Update the configuration of an established trace connection to change its credentials, collection frequency, MID Server, or other settings.
              • Deactivate a trace connection -- Stop trace collection for an established connection without deleting it, so you can reactivate it later.
            • Multi-instance -- The Multi-instance Framework enables a prod (manager) instance to manage multiple sub-prod (managed) instances and facilitate communication for AI Control Tower.
            • Configuring security connections -- Connect AI Control Tower to the platforms where your AI agents run and to your identity provider so that policies and AI agent containment using kill switch protocol can act on agents wherever they're hosted.
              • Add an AWS Bedrock or AWS Bedrock Agent Core connection -- Connect AWS Bedrock or AWS Bedrock Agent Core to AI Control Tower so policies and AI agent containment using kill switch protocol can reach and act on agents running on AWS.
              • Add an Azure AI Foundry connection -- Connect Azure AI Foundry to AI Control Tower so that policies and AI agent containment using kill switch protocol can reach and act on agents running on Azure AI Foundry.
              • Add a Gemini Enterprise Agent Platform connection -- Connect Gemini Enterprise Agent Platform to AI Control Tower using a service account and OAuth 2.0 JWT Bearer authentication, so policies and AI agent containment using kill switch protocol can reach and act on agents running on Gemini Enterprise Agent Platform.
              • Add an Okta connection -- Connect Okta to AI Control Tower so that policies and AI agent containment with kill switch protocol prevent future tokens from being issued to a deactivated AI agent.
              • Add an Agent Client Collector (ACC) connection -- Block and unblock AI usage on managed devices by configuring Agent Client Collector (ACC) as a control enforcement point.
          • Configuring rules and templates -- Configure how AI assets are classified, evaluated, valued, and secured across your organization through rules and templates.
          • AI Gateway -- Route AI agent connections to MCP servers through AI Gateway, so you control which servers and tools agents can reach and what data passes between them.
            • Explore -- Learn how AI Gateway governs connections between AI agents and MCP servers, where you manage it, and how an MCP server is approved for agent traffic.
              • Overview tab -- Use the Overview tab of the AI Gateway settings page to turn connections through AI Gateway on or off, for all MCP servers or for one server.
              • Tools tab -- Use the Tools tab of the AI Gateway settings page to choose whether tools are automatically deactivated after a security scan or activated after approval.
              • Policies tab -- Use the Policies tab of the AI Gateway settings page to activate the Data Sensitivity Check, which helps filter personally identifiable information in MCP traffic.
            • Configure -- Prepare your instance for AI Gateway, bring MCP servers into the inventory and approve them, and choose the settings that apply to your MCP server connections.
            • Connect agents -- Register the clients that can connect to an approved MCP server, and then configure agents to call the server through its AI Gateway MCP server URL.
            • Govern tools and data -- Review scan results for an MCP server's tools, decide which tools agents can call, and choose the tools that the Data Sensitivity Check applies to.
            • Control traffic -- Turn MCP server connections off while you investigate a server, turn them back on when you're done, and review each server's activity.
            • Reference -- Reference topics provide details about the roles and system properties that apply to AI Gateway.
          • AI Control Tower playbooks -- Drive the lifecycle and approval workflows for AI assets using playbooks in AI Control Tower.
            • Updated playbooks for governing managed assets -- Manage AI assets through structured lifecycle workflows using the updated playbooks that automate governance tasks, route approvals, and track compliance requirements across onboarding, maintenance, and retirement phases.
            • Migrate to updated AI asset onboarding playbook -- Configure the new AI asset onboarding playbook to simplify AI asset management through structured lifecycle workflows. The migration also includes an opt-in to decide between moving to the new playbook or continuing in the existing playbook.
          • Configuring ServiceNow AI settings -- Decide what AI data your instance shares with ServiceNow, which AI assets need AI steward approval before deployment, and which AI model providers your AI systems can use.
            • Configuring data controls -- Choose whether your instance contributes data that ServiceNow uses to improve its AI products, and whether ServiceNow Otto traffic can move to Microsoft Azure datacenters during traffic spikes.
              • Opt out of data sharing -- Stop your instance from contributing data that ServiceNow uses to improve its AI models and products.
              • Change the data overflow processing setting -- Keep all ServiceNow Otto traffic in ServiceNow datacenters by opting out of data overflow processing, or opt back in to restore bursting to Microsoft Azure during traffic spikes.
            • Configuring builder controls -- Keep a human review between building an AI asset and deploying it by requiring AI steward approval for each asset type and triggering approval requests automatically.
              • Require AI steward approval for AI assets -- Make sure every AI system, MCP server, or AI model is reviewed before deployment by requiring AI steward approval for that asset type and starting approval requests automatically.
            • Configuring AI model providers -- Limit your AI systems to the model providers your organization approves, control where AI requests are processed, and see how each change affects the AI systems on your instance before you save it.
              • Configure allowed AI model providers -- Restrict your AI systems to the model providers your organization approves, choose where their requests are processed, and decide what happens to AI systems the approved providers don't support.
              • Enroll in the Model Preview Program -- Give your organization early access to AI models before they're generally available by accepting the Model Preview Program terms on an eligible instance.
          • Configuring pages -- View and govern your AI portfolio using terms and visualizations tailored to your organization.
            • Configure a page card -- Change how a card presents its data so that a page matches the terminology, level of detail, and reporting focus your organization works with.
          • Creating or extending pages with pro-code tools -- Extend your AI Control Tower pages beyond the built-in configuration options with the ServiceNow Lux Lab for VS Code extension.
        • Plan your AI strategy -- Define AI strategic priorities, set measurable goals, and track planning items and costs to align your AI investments with organizational objectives.
          • Plan AI strategy, prioritize, and execute -- Track your AI portfolio from strategy to delivery. Plan connects goal alignment, intake management, and execution tracking in one place within AI Control Tower. Portfolio managers and AI COE leads get a current view of AI investments without leaving the application.
            • Explore -- AI Plan in AI Control Tower gives portfolio managers and AI COE leads a single place within AI Control Tower to view goals, intake, and delivery work scoped to AI investments.
            • Configure -- The AI Plan tab in AI Control Tower displays when the Strategic Planning application is installed. It requires no additional configuration once installed.
            • Use -- Use the Strategize, Prioritize, and Execute pages in the Plan menu of AI Control Tower to manage AI work from goal alignment through delivery tracking.
              • Strategize AI plan -- The Strategize tab gives AI stewards a view of the AI strategic direction for their organization. Goals, targets, and strategic priorities that guide AI investment and governance decisions are tracked in one place.
                • Edit a strategize record -- Update the details of an existing goal, target, or strategic priority record to reflect changes in organizational direction, scope, or measurement criteria.
              • Prioritize AI plan intake -- View and manage AI-related intake items, demands, product ideas, and product feedback, through analytics tiles, contextual filters, and filterable lists in Prioritize tab. All three lists support creation of new records from this tab.
                • Create an intake record -- Use the Prioritize tab to add a demand, product idea, or feedback record. Selecting New in any list opens a full form. The form fields differ by record type.
                • Manage intake records -- Update the details of an existing intake record to reflect changes in scope, priority, or other relevant information.
              • Monitor AI Plan execution -- Monitor the delivery status of AI-related projects and epics from a single page in AI Control Tower, with widgets and lists that update dynamically when you apply filters.
            • Reference -- Field descriptions for the Strategize, Prioritize, and Execute forms in the AI Control Tower.
              • Components installed with AI Control Tower for SPM -- User roles are added with the installation of AI Control Tower and Strategic Planning application.
              • Demand form -- Learn about the fields on the Demand form. Use this form to create or edit a demand from the Prioritize page in AI Control Tower.
              • Epic form -- Learn about the fields on the Epic form. Use this form to create or edit an epic from the Execute page in AI Control Tower.
              • Feedback form -- Learn about the fields of the feedback form. Use this form to create or edit the details of a feedback record in AI Control Tower.
              • Goal form -- Use the Goal form to create goals for your organizational strategic priorities.
              • Project form -- Learn about the fields on the Project form. Use this form to create or edit a project from the Execute page in AI Control Tower.
              • Product idea form -- Learn about the fields of the Product idea form. Use this form to create or edit the details of a product idea in AI Control Tower.
              • Strategic Priority form -- Use the Strategic Priority form to orient your organization strategic plan toward your goal.
              • Target form -- Use the Target form to track and measure the progress of the goals.
        • Discover and manage AI assets -- Get a complete picture of every AI system in your organization by building and maintaining a comprehensive AI asset inventory.
          • Discovering AI assets -- Populate your AI asset inventory automatically as AI Control Tower discovers AI assets across external platforms, hyperscaler traces, and your ServiceNow instance.
          • Managing your AI asset inventory -- Track every AI system, model, prompt, and dataset across your enterprise and control which assets participate in governance, monitoring, and risk workflows.
            • Creating AI assets manually -- You can create AI assets manually to track and manage the life cycles of your AI systems, AI models, prompts, and datasets.
            • Reviewing duplicate AI assets -- AI asset deduplication in AI Control Tower identifies duplicate records in the AI asset inventory for AI Stewards to review and consolidate.
            • AI Inventory Intelligence Agent -- AI Inventory Intelligence Agent automatically analyzes the AI asset inventory, identifies assets with incomplete metadata, and generates enrichment recommendations to improve data quality and governance readiness.
            • Managed and unmanaged AI assets -- Control whether an AI asset participates in governance workflows by changing the status in AI Control Tower.
              • Move assets to managed -- Bring discovered or imported AI assets into your governance program by moving them to managed status, making them eligible for lifecycle review, evaluation scoring, risk classification, and value measurement.
              • Move assets to unmanaged -- Remove AI assets from active governance workflows by moving them to unmanaged status, retaining them in the inventory for tracking without incurring subscription charges.
            • Managing AI assets in bulk -- Classify large numbers of AI assets automatically instead of moving them to managed one at a time by creating automation rules.
              • Create an automation rule -- Set the conditions for automatically marking discovered AI assets as managed by creating a custom automation rule.
              • Edit an automation rule -- Change which discovered AI assets a rule marks as managed, or update its name or description, by editing an existing automation rule.
            • Evaluating AI systems -- Monitor the quality and safety of select AI systems by enabling evaluations.
              • Managing evaluation cost -- Reduce the assists that evaluation consumes by adjusting what you evaluate, how often you evaluate it, and which AI systems you evaluate.
              • Enable evaluation for an AI system -- Start generating quality and safety scores for one or more AI systems by enabling evaluation from the inventory.
              • Disable evaluation for an AI system -- Stop generating evaluation scores for one or more AI systems by disabling evaluation from the inventory, while preserving all historical score data.
            • External Registries -- External Registries is the mechanism that lets an AI Steward make a managed AI agent discoverable to external systems.
              • Publish AI agents -- Marking AI agents as publishable from an AI asset record page.
          • Working with AI asset records -- An asset record consolidates the state of a single AI asset and the actions you can take on it, so you can understand the asset's situation and respond from one page.
            • Reviewing AI asset status -- Check the governance posture, pending work, key details, and value delivered by a specific AI asset, and act on what needs attention without leaving the record.
            • Managing AI asset details -- Confirm what an AI asset is, who owns it, how it operates, and what other assets depend on it before approving a change, investigating a score, or responding to an audit question.
              • Update use and purpose -- Update the use and purpose values for an AI asset when its operating characteristics or business outcome change so that risk classifications and governance controls continue to reflect how the asset behaves.
              • Use and purpose fields -- Field and value reference for the Use and purpose section of an AI asset record. AI stewards and AI asset owners reference these values during onboarding, reviews, and audits.
              • Trace AI asset relationships -- Identify the AI assets that depend on or feed into a specific AI asset to assess the impact of a planned change, investigate an unexpected evaluation score, or respond to an audit question about how data and models flow through your AI inventory.
              • Associate a business application with an AI system -- Associate an existing business application with an AI system asset, independently of whether the Enterprise Architecture Workspace plugin is installed.
            • Managing your AI asset lifecycle -- Get a structured view of an AI asset's progression through its operational stages, from initial onboarding to retirement.
            • Planning strategy and execution for an AI system -- View all planning data for a specific AI system in one location. The Plan tab automatically filters goals, intake items, and delivery records to show only those linked to your selected AI system across Strategize, Prioritize, and Execute workflows.
            • Governing AI asset risk and compliance -- Get a consolidated view of your AI asset's regulatory risk classification, compliance posture, control effectiveness metrics, and governance artifacts from the Risk & compliance tab.
            • Monitoring an AI system -- Assess the quality and safety performance of a specific AI system by reviewing its scores, metric breakdowns, trends, and evaluated sessions.
              • Review scores for an AI system -- Determine whether a specific AI system is meeting quality and safety targets by reviewing its scores, identifying which metrics are affecting performance, and checking for regressions over time.
              • Configure metrics evaluated for an AI system -- Add or remove metrics for a specific AI system to tailor evaluation coverage without changing your organization's global metric configuration.
            • Viewing value metrics for an AI system -- View productivity gains, net returns, usage volume, and cost metrics so you can assess the business impact of a specific AI system over time.
            • Viewing templates associated with an AI system -- Learn how value is being measured for an AI system by viewing the value templates mapped to the asset and the productivity calculation each template uses.
            • Governing AI asset security -- Get a snapshot of your AI asset's security posture and visualize how your asset relates to other agentic assets in your enterprise in the AI agent map.
          • Working with MCP server records -- The MCP servers tab on the AI Control Tower Inventory page provides a centralized view of MCP servers registered in your ServiceNow instance.
          • Working with ServiceNow Arc agent records -- Track every installation of ServiceNow Arc across your organization and stop it from running on specific devices, all from one record in the AI Control Tower inventory.
            • Block Arc on devices -- Stop ServiceNow Arc from starting on specific machines when you need to contain its use, without affecting other installations.
            • Unblock Arc on devices -- Let users launch ServiceNow Arc again on machines where you previously blocked it.
        • Govern AI assets -- Govern AI assets across the life cycle with integrated risk, compliance, security, and privacy oversight in AI Control Tower.
          • Managing risk and compliance -- Gain visibility into AI-related risks, compliance posture, and governance outcomes for your AI portfolio in AI Control Tower.
            • Explore -- Risk and Compliance in AI Control Tower provides a summary of regulatory classification, compliance, and risk across your AI portfolio and individual AI assets.
            • Configure -- Risk and Compliance information appears in AI Control Tower only when the required governance applications, frameworks, and data are available in your environment.
            • Reviewing AI governance posture and compliance status -- The Risk & Compliance tab under Govern displays regulatory classification, risk posture, and compliance information for AI assets.
              • Reviewing regulatory classification and compliance status -- Review regulatory risk classification and compliance posture to understand how AI assets align with configured governance expectations.
                • Regulatory risk classification -- Regulatory risk classification places an AI asset in a risk rating, such as Low or High, based on the score from a risk assessment.
                • Compliance score calculation -- The compliance score of an AI system measures how well its controls are met, based on the scores of its active related entities.
              • Reviewing AI risk posture -- Aggregated risk posture displays inherent risk, residual risk, and control effectiveness for AI assets.
                • Risk rating calculation -- The inherent, control effectiveness, and residual ratings of an AI system come from risk assessment scores that a risk rollup aggregates.
              • Governance insights -- Scheduled detection jobs evaluate your AI portfolio and generate the Stalled Lifecycle Tasks and Significant Issues insights that appear as recommendations.
                • Governance insight detection -- Thresholds, criteria, and refresh schedule that determine when an AI system appears in the Stalled Lifecycle Tasks or Significant Issues insight.
              • Act on AI asset governance insight recommendations -- Resolve Stalled Lifecycle Tasks and Significant Issues recommendations to keep AI systems moving through their governance life cycle.
            • Reference -- Review the scope of Risk and Compliance visibility in AI Control Tower, including key terminology used across these views.
              • Terminology -- Key terms used across Risk and Compliance views in AI Control Tower, including compliance score and regulatory risk classification.
              • Governance records -- Record types under the Governance section of an AI asset's Risk & Compliance tab in AI Control Tower, used to support governance review.
              • Regulatory risk classification -- Risk assessment methodologies, formulas, risk ratings, and records that determine the regulatory risk classification of an AI asset.
              • AI risk score calculation -- Formulas, rating bands, lookup matrix, and rollup settings that determine the inherent, control effectiveness, and residual ratings of an AI system.
              • AI system compliance score calculation -- Formula, calculation rules, scheduled jobs, and properties that determine the compliance score of an AI system.
              • Dashboard errors -- Properties and scheduled jobs that resolve No data found errors in the risk score and compliance score dashboards on the AI asset record and landing pages.
          • Managing AI asset security -- Review AI asset security metrics such as access issues, dormant and privileged AI agents, and map the relationships of your ServiceNow agents, agentic workflows, and tools.
            • Explore -- The security area of AI Control Tower offers a dashboard-based view of your AI asset security metrics. In addition to tracking metrics, the security area contains the agent map, a tool that gives a node-graph visualization of the relationships between your AI agents, agentic workflows, and tools.
            • Configure -- Plan and configure your implementation of security metrics. You can configure metrics to measure the integrity of your data model and monitor potential threats in large language model (LLM) input and output. You can also customize the AI asset security score.
              • Configure overview security metrics -- If you have external AI agent data you want reflected in the Privileged AI agents metric, set up a Traceloop connection to the external AI server and perform other setup to make sure agent data appears in the metric. Or, set up a static connection for Amazon Web Services (AWS) or Azure.
              • Configure Veza access intelligence in the agent map -- Integrate Veza with ServiceNow using OAuth 2.0 to display agent risk scores and severity levels in the agent map.
                • Configure OAuth in Veza -- Create an OAuth 2.0 client and an OAuth 2.0 app in your Veza tenant so that AI Control Tower can authenticate to Veza using OAuth 2.0 instead of an API key.
                • Configure OAuth for Veza in ServiceNow -- Set up two application registries, their OAuth entity scopes and credentials, then link them to the pre-provided connection alias, so that AI Control Tower can authenticate to Veza using OAuth 2.0.
              • Activate design-time security metrics -- Set up AI Service Graph Connectors for the AI security tools you currently use to import AI model vulnerability and AI validation (automated red teaming) data and show it in design-time metrics. To see additional metrics, including details for each metric, install the AI Security Exposure Management plugin (com.sn_sec_ai).
              • Configure runtime security metrics -- Set up a Traceloop connection and API key for prompt injection, offensive content, sensitive data input, and sensitive data anonymized trace data from external AI servers. Review data privacy settings to see which patterns detect sensitive data in LLM input and output.
              • Configure post-runtime security metrics -- Customize security and content moderation policies, sampling rate, skill call usage limit, LLMs to use, and other settings for the Top AI asset security events metric and others.
              • Configure the AI asset security score -- Customize the AI asset security score to align with your enterprise's security practices. You can omit large language model (LLM) guardrail categories from the score or change the weights of categories.
              • Configure AI agent containment using kill switch protocol manually -- Connect identity providers and AI agent platforms to ServiceNow to let you contain and enforce guardrails for AI assets at runtime using kill switch protocol.
              • Update system property to limit records -- Update the sn_ai_security.analyzer_max_record_age_hours system property to limit the age (in hours) of AI asset invocation records evaluated for AI asset security metrics.
              • Turn on the AICT Security Analyzer agent -- Turn on the AICT Security Analyzer agent to get additional analysis of AI asset security events. The agent classifies events by severity, adds them to Your top recommendations, and creates relevant security tasks.
            • Discover your agent network with the map -- Use the agent map to visualize your entire agentic ecosystem, including ServiceNow and third-party AI assets.
            • Monitor AI asset security events and recommendations -- Triage and resolve AI recommendations and AI asset security events to optimize AI asset security.
            • Contain AI agents manually using kill switch protocol -- Deactivate or reinstate AI agents using kill switch protocol to help improve your security posture and stop malicous activity.
              • Review the agent containment list -- The agent containment list shows agents that were deactivated and reinstated for the instance manually with kill switch protocol or automatically by policy enforcement. You can view audit log information for each AI agent which can help you stay compliant with regulatory guidance and your business rules.
            • Reference -- Reference topics provide additional details about the charts and metrics that you use to assess your AI asset security posture in AI Control Tower.
              • System properties -- System properties that connect Veza access intelligence and limit the age of records evaluated for AI asset security metrics are available. Limiting records can prevent analyzing stale data and reduce unnecessary processing overhead.
          • Controlling AI asset usage -- Create AI asset usage policies that automatically respond to detected AI threats or block an AI agent, domain, or model outright.
            • Explore -- Learn how policies let you automatically respond to detected AI threats, block AI usage outright, or control what Arc can do on your users' devices, and where policies are enforced across AI Control Tower.
              • Threat Response -- Automatically contain an AI agent the moment it crosses a risk threshold you define, instead of waiting for someone to notice and act.
              • Explicit Block -- Stop a specific person, a department, or your whole organization from using an AI agent, model, or domain, enforced automatically everywhere that access could happen.
              • Arc policies -- Control which tools, commands, network destinations, files, and connector permissions ServiceNow Arc can use on your users' devices, and which actions wait for a person's approval, from AI Control Tower.
            • Configure -- Set up policies in AI Control Tower by configuring control enforcement points.
              • Configure AI agent containment automatically -- Connect an identity provider and the AI agent runtime platforms to AI Control Tower so a Threat Response policy can automatically contain an AI agent using kill switch protocol.
            • Managing policies -- Create, change, or remove the policies that respond to detected threats or block AI usage.
            • Managing Arc policies -- Create and manage ServiceNow Arc policies that control what Arc can do, which actions need approval, and which actions are blocked.
              • Policy stacking and precedence -- When more than one policy applies to a user, Arc merges them into one effective policy and resolves any conflicts by priority, specificity, and restrictiveness.
              • Create an Arc policy -- Give a team its own ServiceNow Arc rules by creating a policy that applies to the users you choose and takes precedence over the default Arc policy.
              • Working with Arc policy rules -- Add and customize the rules that control what Arc can do for the users a policy covers.
                • Action approval flow in ServiceNow Arc -- Tool gates, approval patterns, and auto approval decide whether each action Arc attempts runs, waits for a person's approval, or is blocked.
                • Create a tool gate -- Decide how ServiceNow Arc handles a tool, such as the shell or an MCP server tool, by letting it run, blocking it, or sending its calls for review.
                • Create an approval pattern -- Pause destructive or outbound commands for a person's decision, or let trusted routine commands run without a prompt, by matching them with an approval pattern.
                • Create a network rule -- Open a destination that ServiceNow Arc needs to reach, or block one it shouldn't, by adding a network rule for the users a policy covers.
                • Create a file type rule -- Keep sensitive file types out of reach of ServiceNow Arc by setting whether the agent can read, write, or not access files with specific extensions.
                • Create a sandbox rule -- Restrict the reach of ServiceNow Arc agent commands by limiting the paths, binaries, system calls, and environment variables the sandbox can use.
                • Create a connector scope -- Limit what ServiceNow Arc can do through a connector, such as reading mail without sending it, by granting only the connector operations a team needs.
                • Create a capability override -- Turn a ServiceNow Arc feature on or off, or change a limit, for the users a policy covers without changing the default for anyone else.
                • Edit an Arc policy rule -- Adjust how an existing ServiceNow Arc rule behaves, such as a gate mode, a pattern's priority, or a network destination, without recreating it.
                • Remove an Arc policy rule -- Stop applying a rule to the users an ServiceNow Arc policy covers by removing it from that policy, while other policies that use the rule keep it.
              • Edit an Arc policy -- Change who an ServiceNow Arc policy applies to, how much weight it carries, or whether it's enforced, without rebuilding its rules.
              • Delete an Arc policy -- Return a group of users to the behavior of their remaining ServiceNow Arc policies, such as the default Arc policy, by deleting a policy you no longer need.
            • Reviewing enforcement activities -- Review policy activities and execution results.
            • Reference -- Reference topics provide additional information about threat types and where policies are enforced.
        • Monitor AI assets -- Evaluate the quality and safety of AI interactions across your portfolio using automated scoring, configurable metrics, and trend analysis for both ServiceNow and external AI systems.
          • Monitoring and evaluating AI systems -- Continuously monitor your ServiceNow and external AI systems to determine whether they meet quality and safety standards, and investigate root causes when they don't.
            • Explore -- Learn how AI Control Tower automatically scores live AI interactions against quality and safety metrics using an OpenTelemetry-based data model of sessions, traces, and spans.
              • Sessions, traces, and spans -- Understand the three levels of AI interaction data that AI Control Tower uses to structure, score, and display runtime behavior.
              • How evaluation scoring works -- Understand how AI Control Tower calculates quality and safety scores so you can interpret results accurately and configure scoring to reflect your priorities.
              • Evaluation scoring examples -- Worked scoring examples show how metric configuration, weights, and evaluation levels combine to produce quality and safety scores for different AI system types.
              • Monitoring and value -- Quality scores from monitoring can feed the value calculation. The value an AI system reports then reflects how well it performs, not just how often it is used.
            • Configure -- Set up monitoring in AI Control Tower by activating evaluations, adding metrics, and configuring metric templates.
            • Reviewing scores -- Determine whether your AI systems are meeting quality and safety targets by reviewing scores and evaluation trends.
              • Monitoring overview -- Identify low-scoring AI systems quickly by reviewing quality and safety scores, AI-generated insights, and performance trends across your AI portfolio.
              • Review scores across your AI portfolio -- Assess the quality and safety of your AI systems by reviewing scores, identifying low-scoring systems, and learning which metrics are affecting each score.
            • Investigating sessions -- Narrow a quality or safety issue from a broad score to a specific cause by reviewing evaluated sessions and session details.
              • Evaluated sessions -- View all evaluated AI sessions across your portfolio, compare quality and safety scores by AI system, and identify the sessions that need investigation.
              • Session details -- View metric breakdowns, the judge's reasoning, and trace and span data for a specific evaluated session.
              • Investigate a low-scoring session -- Determine the root cause of a low quality or safety score by working through the session detail, trace timeline, and span-level input and output data.
            • Reference -- Reference topics provide additional information about the evaluation metrics in AI Control Tower.
              • Evaluation metrics -- All evaluation metrics available in AI Control Tower, with their categories, evaluation levels, scoring formats, and descriptions.
        • Measure AI systems -- Measure quantifies the productivity value delivered by your AI systems and tracks their costs. It also reports the net return on AI, enabling you to determine where to scale, fund, or retire AI.
          • Measure AI system -- Measure is the AI Control Tower capability for measuring the productivity gains, cost, and net AI return of your AI systems. It brings together value measurement, cost tracking, and dashboards.
            • Explore -- Measure helps you determine whether your AI systems deliver more value than they cost. It brings value and cost data together in dashboards so that you can compare productivity gains with AI spend.
              • Value -- Value translates AI usage into measurable productivity metrics.
                • Templates -- Value templates define how AI Control Tower calculates the productivity value of an AI system. Each template captures a persona, usage indicators, a time value type, and a quality score.
                • Calculation and Value jobs -- Value jobs calculate the productivity value of your AI systems on a schedule. Automated jobs run each night, and manual jobs run monthly or quarterly for AI systems that you onboard manually.
                • Formula and metrics -- AI Control Tower calculates the productivity value of an AI system by multiplying usage, time saved per invocation, and the acceptance rate.
                • Value tracking -- The AI Control Tower value dashboard shows value and usage only for AI systems that were managed during the reporting period. Value realized while an AI system was managed stays on the dashboard, even after the AI system becomes unmanaged.
                • Multi-Instance Framework (MIF) -- The Multi-Instance Framework (MIF) synchronizes AI value data from a sub-production instance to a production instance only for Creator skills. In this setup, AI Control Tower calculates value for Creator skills using data from development and testing environments.
              • Cost -- Cost records the actual expenses associated with your AI systems, enabling AI Control Tower to compare these costs against productivity gains and calculate the net return on investment.
                • AI cost and net AI return -- AI Control Tower tracks the cost of your AI systems and subtracts it from the productivity value to show the net AI return. Cost is tracked by vendor from token consumption or a direct cost.
                • Cost types and sub-vendor rates -- Record what your organization pays each AI vendor so that AI Control Tower can calculate total Enterprise AI cost and net returns. Choose the cost type that matches each contract, and set sub-vendor rates where a specific service is billed differently from its vendor.
                • Subscription-based costs -- Use the Subscription cost type in AI Control Tower to track vendor costs billed per licensed seat under a fixed-term contract rather than by token or usage.
                • Cost updates and calculation schedule -- AI Control Tower preserves recorded cost data and calculates cost and value on a daily schedule. These rules determine when a cost change takes effect and when it appears in your dashboards.
              • Dashboards -- Dashboards provide insights into the productivity gains, costs, and net returns of the AI systems within your enterprise. There are distinct dashboards for reporting on vendors and ServiceNow AI, ensuring that enterprise-wide metrics remain separate from those specific to ServiceNow AI systems.
                • Value dashboard -- The Value dashboard provides real-time visibility into the productivity gains and financial returns delivered by your AI Control Tower agents. Track hours saved, cost savings, net returns, and system performance to measure ROI and demonstrate AI investment impact.
                • Engagement dashboard -- The Engagement dashboard provides visibility into AI system usage patterns across your organization, including adoption metrics, department usage, and system adoption by geographic region.
                • ServiceNow AI dashboard -- The ServiceNow AI dashboard is a central hub for monitoring and evaluating the performance, adoption, and financial impact of AI systems deployed across your ServiceNow environment.
                  • Value dashboard -- The ServiceNow AI Value dashboard provides a comprehensive view of AI system performance, value delivery, and operational metrics across your organization. The dashboard displays productivity gains, financial returns, system usage patterns, and agent performance data.
                  • Engagement dashboard -- The ServiceNow AI Engagement dashboard provides visibility into user adoption, utilization patterns, and performance metrics across all AI systems in your ServiceNow instance. Monitor AI action volume, user engagement trends, departmental usage, and task efficiency gains to identify adoption opportunities and system effectiveness.
                  • Creator skills dashboard -- The ServiceNow AI Creator skills dashboard provides insight into how your organization uses AI-powered creator skills—automated code generation, documentation, and testing capabilities—to boost developer productivity. Monitor skill satisfaction, usage patterns, and outcomes to optimize adoption and identify high-performing skills across your instance.
                  • Evaluation dashboard -- Use the ServiceNow AI Evaluation dashboard to get a comprehensive visibility into AI agent performance.
                    • Conversation evaluation -- The ServiceNow AI Conversation evaluation dashboard displays AI response quality metrics and satisfaction scores for individual conversations. It includes detailed evaluation records with human feedback and automated scoring across quality dimensions such as intent accuracy, request completion, truthfulness, and context retention.
                    • Impact evaluation -- The ServiceNow AI Impact evaluation dashboard displays business outcomes and operational results from AI conversations. Metrics include issue resolution rate, time saved, cost reduction, and other KPIs demonstrating AI business value.
              • Role based data visibility -- AI Control Tower shows value, engagement, and cost data for the AI systems in a user’s scope. AI stewards can view data for all AI systems in an instance. Product owners can view data only for the AI systems that they manage.
              • Conversational evaluator -- Conversational evaluator measures the quality of Virtual Agent conversations in AI Control Tower.
            • Configure -- Set up default template rules, the value job user, AI cost, and usage tracking so that AI Control Tower can calculate value and cost.
              • Value -- Configure the value templates, value jobs, and calculation settings that AI Control Tower uses to measure the business value of your AI systems.
                • Review or create default template rules -- Assign a default value template to each AI system category and vendor so that newly onboarded AI systems are mapped automatically.
                • Create and publish a value template -- A value template defines the formula used to calculate productivity gains for mapped AI systems. After you publish a template, the value job runs automatically and populates the Value dashboard.
                • Edit a published value template -- Change the department, description, or AI system mappings of a published value template, and remove templates that you no longer need while keeping value calculation uninterrupted.
                • Assign the value job user -- Assign an active user to run value jobs so that AI Control Tower can calculate value. When the assigned user is inactive, value calculation stops.
                • Create and run manual value jobs -- Set up manual value jobs for AI systems that you onboard manually, so that AI Control Tower calculates their value on a monthly or quarterly cadence.
                • Set up MIF for value calculations -- Connect a sub-production instance to a production instance through the Multi-Instance Framework (MIF) so that AI Control Tower can run value calculations across Creator skills.
                • Move an unmanaged AI system to managed -- When an AI system is unmanaged, its value data stops appearing on the value dashboard and its value templates are unpublished. Move it back to managed in AI Control Tower to restore value tracking.
                • Set look back date range -- Change how many days of missing value data AI Control Tower fills in when you mark an unmanaged AI system as managed again.
              • Cost -- Configure the hourly rates and vendor costs that AI Control Tower uses to calculate what your AI systems cost to run.
                • Configure hourly rates -- Set the average hourly rate that the Cost Framework uses to convert hours saved into financial savings.
                • Add integrated vendor cost -- Add the cost of a vendor or sub-vendor integrated with ServiceNow so that AI Control Tower includes it in the total Enterprise AI cost. Set a sub-vendor rate when a specific service is billed differently from the vendor.
                • Add other vendor costs -- Configuring costs for LLM vendors without direct integrations with AI Control Tower requires manual input. You must manually enter token usage, direct costs, or a per-seat subscription. AI Control Tower can then include these costs in total AI cost calculations.
                • Review and submit the cost configuration -- Review all Cost Framework configurations, verify the calculations, and submit to activate the Cost Framework.
              • Dashboards -- Configure the tracking settings that determine which usage data appears on the dashboards in AI Control Tower.
            • Use -- Use Dashboards to review and analyze the productivity gains, AI costs, and the net return on AI investment.
              • Review value and engagement insights for AI systems -- Use AI Control Tower to review productivity gains, cost savings, and engagement results for AI systems in your scope. AI stewards review data for all AI systems on the instance. Product owners review data for the AI systems that list them in the Managed by field.
              • Evaluate conversations -- Use Conversational Evaluator in AI Control Tower to review conversation quality scores, and estimate the cost savings from Virtual Agent conversations.
            • Reference -- Reference topics provide additional information about the required roles and Performance Analytics indicators, and the tables used in the value calculation.
              • PA indicators and tables -- Learn about the out-of-the-box Performance Analytics (PA) indicators and the database tables that AI Control Tower uses to calculate value.
              • Feature access by role -- Access to features varies by role. The value, engagement, and cost features differ between AI stewards and product owners.
        • Address action items -- Track and act on the governance work and AI-generated recommendations that AI Control Tower surfaces for you in Activity Center.
          • Managing tasks and approvals -- Track and resolve the governance work that AI Control Tower generates as your AI portfolio grows, such as lifecycle tasks, security tasks, cases, and risk assessments.
            • Lifecycle tasks -- Advance managed AI assets through controlled stages of governance by completing the reviews, assessments, and approvals that AI asset lifecycle playbooks require.
              • Complete a lifecycle task -- Advance a managed AI asset through its lifecycle by completing the reviews, assessments, or approvals that an asset lifecycle playbook requires.
            • Security tasks -- Address possible security threats, policy violations, and access issues on managed AI assets by acting on the security tasks the system generates for AI stewards and security reviewers.
              • Resolve a security task -- Investigate a security concern that AI Control Tower has detected on a managed AI asset, take the appropriate remediation action, and document the resolution.
            • Change and offboarding requests -- Make controlled changes to a managed AI asset, or retire an asset that is no longer needed, by submitting a request for AI steward review and approval.
              • Review and approve a change request -- Evaluate a change request submitted by an asset owner and either approve the change so AI Control Tower can apply it, or reject the change so the asset remains unchanged.
              • Review and approve an offboarding request -- Evaluate an offboarding request submitted by an asset owner and either approve the request to move the asset into the offboarding lifecycle, or reject the request so the asset remains active.
            • AI cases -- Investigate and document an incident affecting an AI asset, such as a suspected security breach, data exposure, or policy violation, using a structured case record.
              • Create an AI case -- Open an AI case to investigate and document an incident affecting an AI asset, such as a suspected breach, data exposure, or policy violation.
            • Risk assessments -- Complete a risk assessment that AI Control Tower generates automatically for a managed AI asset, evaluating its inherent, control, and residual risk.
            • Issues -- Track a problem identified with an AI asset, such as a performance or compliance gap, through to resolution with a documented action plan.
              • Create an issue -- Track a problem identified with an AI asset, such as a performance or compliance gap, and document the action plan for resolving it.
            • Attestations -- Respond to a request to acknowledge a compliance policy that applies to a managed AI asset you own or steward.
            • Policy exceptions -- Request an approved, time-bound deviation from a policy or control objective that applies to an AI asset.
              • Create a policy exception -- Request an approved, time-bound deviation from a policy or control objective that applies to an AI asset, supported by a justification and a risk assessment.
            • AI inquiries -- Ask a question or request information related to AI governance, such as a question about a policy, a process, or a specific AI asset.
              • Create an AI inquiry -- Submit an AI inquiry to ask a question or request information related to AI governance, such as a question about a policy, a process, or a specific AI asset.
          • Resolving AI recommendations -- Resolve the AI recommendations that AI Control Tower generates when it detects an issue or an opportunity in your AI portfolio, using AI automation, a guided AI conversation, or your own review.
            • Resolve an AI recommendation -- Address an issue or opportunity by running an unsupervised agent, working through a guided conversation with a supervised agent, or resolving the issue yourself.
        • Reference -- Reference topics provide additional information about the roles, tables, data model attributes, and form fields used to configure and administer AI Control Tower.
          • Installed components -- Several types of components are installed with activation of AI Control Tower, including plugins, user roles, and tables.
          • Installation and upgrade considerations -- Upgrading AI Risk and Compliance, Enterprise Architecture Workspace, and AI Control Tower Core out of sync with each other temporarily affects the AI system-to-business application association.
          • GenAI plugin agents and skills inventory -- The ServiceNow Otto for AI Control Tower plugin (com.sn_aict_genai) includes agents and skills that enhance the AI asset management and governance.
          • AI Control Tower email notifications -- Identify the email notifications that AI Control Tower sends automatically, the events that trigger each notification, and the recipients. These notifications keep AI Stewards, asset owners, and assignees informed so that they can take action promptly on AI asset approvals and lifecycle events.
          • Domain separation and AI Control Tower -- Domain separation is supported for AI Control Tower. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
          • System properties -- Several system properties that affect core AI Control Tower are available.
      • AI Control Tower (legacy) -- The AI Control Tower is a platform that connects different parts of an organization to speed up the AI adoption.
        • Exploring AI Control Tower (legacy) -- Explore and learn about the AI Control Tower and its role in managing the AI asset inventory, overseeing configurations, integrating with other applications, and handling the asset approval workflow.
          • AI Control Tower dashboard -- The AI Control Tower dashboard displays a comprehensive overview of the AI status, AI inventory, and other AI related metrics.
            • AI Control Tower Home -- Explore the AI Control Tower home page.
              • Overview tab -- Explore the overview tab in AI Control Tower and the widgets available on the tab.
              • AI strategy tab in AI Control Tower -- The AI strategy tab includes information about all the AI-related priorities, goals, planning items, and execution items—projects and demands in the AI Control Tower workspace.
              • AI asset inventory tab in AI Control Tower -- The AI asset inventory includes all the AI-related assets used by an organization, including AI models, prompts, systems, and databases.
              • Value tab in AI Control Tower -- Use the Value dashboard page to gain insights into the value realized from multiple types of AI in your organization.
              • Adoption tab in AI Control Tower -- Use the Adoption dashboard page to view data about user engagement and feedback, and adoption of every type of AI.
              • Health tab -- Monitor the performance of guardrails enabled through AI Guardian.
              • Risk and compliance tab in AI Control Tower -- The Risk and compliance tab on the AI Control Tower displays the risk classification of AI assets and the compliance posture for selected authority documents and policies.
              • AI cases tab in AI Control Tower -- Track, monitor, and analyze your AI case workflows, identify your workflow bottlenecks, and check your accountability of your AI-related risks by using the AI risk and compliance dashboard. As an AI steward, you can also use the dashboard to track the status and trends of your AI-related inquiries.
              • Evaluation tab -- The Evaluation tab contains the Evaluation dashboard, which is designed to measure, automate, and improve the quality of interactions with Virtual Agent. This dashboard addresses several key challenges to enhance the end-user experience and overall virtual agent utility.
                • Value tab -- The Value tab in the Evaluation dashboard displays the value, efficiency, and time savings of the virtual agent. The information on this tab gives you a transparent and reliable estimation of the value delivered by the virtual agent, focusing on a quality-adjusted calculation of the time saved for users.
                • Human feedback for evaluations -- Expand the Human feedback section to see details on evaluations and their satisfaction scores.
                • Enabling evaluations -- Evaluate random conversations by enabling continuous monitoring.
                • Configuring evaluations -- Configure conversation evaluations by disabling evaluations, adjusting execution logic and thresholds, and tuning scoring weights.
              • Security & Privacy tab in AI Control Tower -- Review AI security metrics such as access issues, dormant and privileged AI agents, and map the relationships of your ServiceNow agents, agentic workflows, and tools.
              • AI Gateway tab -- Explore the AI Gateway tab in the AI Control Tower.
            • AI assets -- An AI asset refers to a digital tool or resource that uses artificial intelligence to carry out particular tasks or address problems. Examples include machine learning models, chatbots, natural language processing systems, image recognition software, and similar technologies.
              • AI asset inventory -- AI asset inventory includes all the AI assets such as AI models, AI systems, prompts, datasets, and MCP servers that an organization can use.
              • AI asset lifecycle -- The AI asset life cycle defines the series of stages that you must follow to manage an AI system, AI model, prompt, or dataset throughout its useful life.
              • Approvals -- The approvals are requests created to either approve or reject an asset. The Approvals menu displays a list of Now Assist approvals.
              • Cases -- You can view all the assigned and unassigned AI cases in a list view in the AI Control Tower.
              • Inquiries -- You can view all the assigned and unassigned inquiries in a list view in the AI Control Tower.
              • AI strategies and goals -- You can track and monitor the progress of your strategic priorities, goals, planning items, and execution items—projects and demands classified as Artificial Intelligence in other ServiceNow applications.
              • AI Task -- Use the All Security Tasks tab to view all AI security tasks for your instance. You can also create an AI task on this page.
            • Configurations -- Explore the AI Control Tower Configurations page to manage and govern ServiceNow AI assets.
              • Data sharing, Data overflow processing, and Security & privacy in AI Control Tower -- Explore the Data sharing, Data processing, and Security & privacy sections.
              • Controls -- Explore the Controls section on the configurations page of the AI Control Tower.
              • Multi-instance Setup -- The multi-instance setup enables a prod (manager) instance to control, manage, and communicate with multiple sub-prod (managed) instances for AI Control Tower.
              • AI Gateway -- Explore the AI Gateway page and its tab in the AI Control Tower Configurations.
              • Playbooks -- The Playbook templates list has a record of Approval Playbook for Now Assist approvals and Asset lifecycle playbook templates.
          • Product Owner portal -- Explore the product owner view and navigate through the accessible tabs on AI Control Tower to ensure a comprehensive understanding of the features.
            • My overview tab -- The My overview tab in the AI Control Tower home page displays all active assets to the asset owner and the AI stewards for assets that they manage or own.
            • AI portfolio tab -- The AI portfolio tab in the AI Control Tower home page displays all AI assets, which includes (active, inactive, and completed) to the workspace users.
            • Business portfolio tab -- The Business portfolio tab on the AI Control Tower home page displays AI adoption trends across your business application portfolio.
          • Definitions of AI asset inventory -- Explore AI asset inventory, and AI assets.
            • AI systems -- Explore AI systems in detail with examples.
              • Example of an AI system -- The AI Control Tower application and the AI Risk and Compliance application play a critical role in managing and governing the responsible use of AI systems, especially in high-stakes domains such as banking and finance.
            • AI models -- Explore AI models in detail with examples.
            • Prompts -- Explore prompts in detail with examples.
            • Datasets -- Explore datasets in detail with examples.
          • Inter-dependencies -- Explore the inter-dependencies of AI systems, AI models, and datasets.
          • Explore Third-party LLMs and regions -- Explore all the scenarios for configuring third party LLMs and SLMs based on the regions.
          • Explore Now Assist AI asset discovery -- Explore the syncing process of AI assets including models, datasets, prompts, skills, and agentic AI components into the AI Asset Inventory of AI Control Tower.
          • Enterprise AI discovery: Unlock Visibility, Governance & Value -- Explore Enterprise AI discovery, its key benefits, and capabilities.
            • AI connections -- Explore the AI connections page and its features.
            • Service Graph Connectors for AI Control Tower -- You can use Service Graph Connectors (SGC)  to import and integrate third-party data into  CMDB  and non-CMDB  tables to create AI connections.
              • AWS -- Use the  AI Service Graph Connector for Amazon to discover AI assets such as AI systems, agents, models, tools, and prompts and well as usage data for these AI agents in AI Control Tower. This usage information is consumed by the AI Control Tower value dashboard.
              • GCP Vertex AI -- Use the  AI Service Graph Connector for GCP Vertex AI plugin to create AI connections to discover AI assets such as AI systems, models, prompts, and tools as well as usage data for these AI agents in AI Control Tower. This usage information is consumed by the AI Control Tower value dashboard.
              • IBM -- The AI Service Graph Connector for IBM enables you to discover and import AI assets from your IBM environment into ServiceNow AI Control Tower.
                • Create an AI connection for IBM -- Create an AI connection for IBM in AI Control Tower using the  AI Service Graph Connector for IBM.
                • IBM APIs -- Explore the IBM APIs used by the AI Service Graph Connector for IBM
                • Data mapping -- The AI Service Graph Connector for IBM uses separate data sources and staging tables for each asset type, per service. The staged data is transformed and loaded into target CMDB tables.
                • Target CMDB classes -- When you complete setting up the connection, you can configure the integration to periodically pull data from IBM. The data is saved in tables that extend from the Configuration Item [cmdb_ci] table.
                • Properties -- AI Service Graph Connector for IBM properties control the behavior of the connector.
              • LangGraph -- Use the  AI Service Graph Connector for LangGraph to discover AI assets such as AI systems, agents, models, tools, and prompts and well as usage data for these AI agents. This usage information is consumed by the AI Control Tower value dashboard.
                • Create an API Key for LangGraph -- Create an API Key for the AI Connector to authenticate with LangGraph.
                • Create AI connection for LangGraph -- Use the AI Service Graph Connector for LangGraph plugin to create AI connections to discover AI assets such as AI systems, models, prompts, and tools as well as usage data for these agents. This usage information is consumed by the AI Control Tower value dashboard.
                • APIs used for LangGraph connector -- Explore the AWS APIs used in AI service Graph Connector for LangGraph.The table lists all the LangSmith API endpoints used by the connector.
                • Target tables for LangGraph -- Target tables for storing Service Graph Connector for LangGraph data.
              • Microsoft -- Use the  AI Service Graph Connector for Microsoft  plugin to create AI connections for Azure Foundry and Copilot to discover AI assets such as AI systems, models, prompts, and tools as well as usage data for these AI agents in AI Control Tower. This usage information is consumed by the AI Control Tower value dashboard.
              • n8n -- Use the  AI Service Graph Connector for n8n to create AI connections to discover AI assets such as AI systems, models, prompts, and tools as well as usage data for these AI agents.
                • Create an API Key in n8n environment -- Creating a API key in n8n environment using your n8n instance.
                • Create an AI connection for n8n -- Use the  AI Service Graph Connector for n8n  to discover AI assets such as AI systems, models, prompts, and tools well as usage data for these AI agents. This usage information is consumed by the AI Control Tower value dashboard.
                • Properties for n8n -- Service Graph Connector for n8n properties control the behavior of the connector.
                • Target tables for n8n -- When you complete setting up the connection, you can configure the integration to periodically pull data from a n8n project. The data is saved in tables that extend from the CMDB CI classes and other non-CMDB classes.
              • OCI -- The AI Service Graph Connector for OCI enables you to discover and import AI assets from your OCI environment into ServiceNow AI Control Tower.
                • Create an AI connection for OCI -- Create an AI connection for OCI in AI Control Tower using the  AI Service Graph Connector for OCI.
                • OCI APIs -- Explore the OCI APIs used by the AI Service Graph Connector for OCI
                • Data mapping -- The AI Service Graph Connector for OCI uses separate data sources and staging tables for each asset type, per service. The staged data is transformed and loaded into target CMDB tables.
                • Target CMDB classes -- When you complete setting up the connection, you can configure the integration to periodically pull data from OCI. The data is saved in tables that extend from the Configuration Item [cmdb_ci] table.
              • Salesforce -- Use the  AI Service Graph Connector for Salesforce to discover AI assets such as AI systems, agents, models, tools, and prompts and well as usage data for these AI agents. This usage information is consumed by the AI Control Tower value dashboard.
                • Create AI connection for Salesforce -- Use the AI Service Graph Connector for Salesforce plugin to create AI connections to discover AI assets such as AI systems, models, prompts, and tools as well as usage data for these AI agents in AI Control Tower. This usage information is consumed by the AI Control Tower value dashboard.
                • APIs used by Salesforce -- Explore the Salesforce APIs used in AI service Graph Connector for Salesforce. The table lists all the Salesforce API endpoints used by the connector.
          • AI Gateway -- Explore the AI Gateway, its value and learn how to use and configure it for your MCP (Model context protocol) transactions.
          • spm-integration-with-ai-control-tower --
        • Configuring AI Control Tower (legacy) -- Configure the AI Control Tower workflow.
        • Using AI Control Tower (legacy) -- Use AI Control Tower for creating governance workflows.
        • AI Control Tower reference (legacy) -- Reference topics for AI Control Tower.
      • AI Risk and Compliance -- The AI Risk and Compliance (AIRC) application gives your risk and compliance team a dedicated workspace to assess AI-specific risks, attest to controls, demonstrate regulatory compliance, and manage AI-related cases for the AI capabilities and other AI assets your organization deploys.
      • AI Guardian -- AI Guardian provides the runtime protection layer for your generative AI deployments, evaluating requests and responses in real time to detect offensive content, prompt injection attacks, and sensitive topics that aren't suited for an AI response.
    • Large language models and providers -- Large language models (LLMs) power every Now Assist generative AI capability. Understand how LLMs work on the ServiceNow AI Platform, choose model providers, and write effective instructions.
      • Large language models -- ServiceNow AI Platform utilises large language models (LLM) for generative AI and agentic AI functionality. You can choose the ServiceNow LLM or supported third-party models. LLMs bring about the Generative AI application capabilities by understanding and generating human language, and processing vast amount of data.
        • Model provider updates -- Review these updates to learn which model providers and models are available for your skills and agents. Review the model cards for information about how each model is intended to be used.
        • Writing instructions for large language models -- When using Now Assist products and skills, you may have the option to give specific instructions or other guidance to the LLM. Writing generative AI instructions is different from conducting a keyword search. Use the following general guidelines when crafting your instructions.
        • Discrepancies when using different AI search tools -- Different AI search tools may return different answers for the same or similar searches. This difference in results is expected. It occurs because each large language model (LLM) uses a different approach to find results and generate answers that match your search.
        • Providers and Models -- You can bring your own large language model (LLM) provider and API to use with Now Assist.
    • Managing data for AI -- Build the data foundation and search infrastructure that AI capabilities depend on to deliver accurate, relevant results.
    • Generative AI skills -- Generative AI skills use large language models to enterprise data to complete tasks within workflows. You can activate and configure skills, or build custom skills for your organization.
      • Understanding generative AI skills -- Generative AI skills use large language models to process your enterprise data to complete a single, well-defined task within a workflow, such as summarizing a record, drafting a reply, or recommending a next action. Skills reduce manual effort in work your users already do, without changing how they work.
      • AI assets on by default -- Starting with the Zurich Patch 4 release, some AI agents, generative AI skills, and agentic workflows are turned on by default in the ServiceNow AI Platform.
      • Skills -- ServiceNow AI Platform products contain generative AI skills that are tailored to meet the needs of users in different workflows.
        • Skills in the Platform workflow -- Most Now Assist generative AI products include skills in the Platform workflow, such as product navigation. Some Now Assist products include skills for the conversational user and platform experience, as well as knowledge article recommendations.
          • Article optimization -- The article optimization skill in ServiceNow AI Platform provides recommendations for improving the quality and health of knowledge articles, providing actionable feedback to authors and managers. The recommendations for knowledge articles become available after you activate the Article Optimization skills in Now Assist Admin.
          • Catalog item form slot-fill -- With the catalog item form slot-fill skill, Now Assist can automatically complete catalog item forms based on what users search for.
          • Conversational Help -- This skill uses Generative AI application capabilities to provide answers to the questions on the Now Assist panel.
          • Extract information from documents -- The extract information from documents skill allows you to use Now Assist predictions to extract information from document and image files.
          • Knowledge content recommendation -- Knowledge generative AI skills on the ServiceNow AI Platform provides recommendations for editing a knowledge article. Once activated, this skill is available on the ServiceNow Otto context menu.
          • Navigation -- Use the navigation skill in Now Assist to take you where you want to go on the ServiceNow AI Platform.
          • ServiceNow Otto in Standard Ticket Page -- The ServiceNow Otto in Standard Ticket Page skill allows you to display summaries generated by ServiceNow Otto, providing overviews of recent activities and ticket details.
          • Potential knowledge gaps -- The Potential Knowledge Gap helps in finding missing or incomplete knowledge coverage by analyzing service interactions. Gap recommendations is set to available after you activate the Knowledge Gaps skills in AI Admin Hub.
          • Requester approval checklist skill -- The requester approval checklist skill in the ServiceNow AI Platform generates a structured checklist by mapping real-time request data against your organization’s knowledge articles.
          • Smart Documents Skill -- Accelerate document insights with instant summaries, interactive Q&A, and FAQs using Now Assist in Document Management.
      • AI Skill Kit -- Use ServiceNow AI Skill Kit to create and publish custom prompts and skills for ServiceNow Otto. Creating custom skills and prompts gives you greater flexibility with ServiceNow Otto's generative AI capabilities.
        • Exploring AI Skill Kit -- Use the AI Skill Kit plugin for ServiceNow Otto to create and activate custom prompts and skills for Otto.
          • General guidelines for AI Skill Kit -- Building a custom skill in AI Skill Kit follows five phases, from scoping the skill to deploying and monitoring it.
            • Skill scoping guidelines -- Scope a custom skill before you build it to define its requirements and expected outcomes.
            • Dataset guidelines for AI Skill Kit -- A representative, appropriately sized, and isolated dataset gives you a reliable measure of how your skill prompt performs.
            • Prompt development guidelines -- Write a skill prompt that is specific, clear, and grounded in context so that the model is more likely to return the output that you expect.
            • Prompt evaluation guidelines -- Evaluate a skill prompt during development and again before deployment, using batches of test data and metrics that suit your use case.
            • Deploying and monitoring the skill -- After you evaluate the prompt, you can deploy the custom skill and monitor its effectiveness.
          • Example use case for AI Skill Kit -- As an AI developer, you can create custom skills with AI Skill Kit. For this example, create a custom skill for child incident summarization.
        • Configuring AI Skill Kit -- Configure prompts and skills for AI Skill Kit.
          • Configure a skill prompt -- Configure a skill prompt to set its large language model (LLM), the randomness of its responses, and its token limits.
          • Configure deployment and skill settings -- Configure where a skill appears in AI Admin Hub, review general information, set security controls, choose a provider, and add evaluation metrics.
          • Configure security controls for a skill -- Define an access control list (ACL) and role restrictions for every skill. The ACL limits which user roles can access and run the skill, and role restrictions limit the roles that the skill runs with.
        • Using AI Skill Kit -- Use AI Skill Kit to create and publish prompts and custom skills for Otto.
          • Create a skill -- Create a custom skill for Otto. Custom skills extend the generative AI capabilities of Otto to fit your own use cases.
            • Clone and edit a ServiceNow skill -- Clone an eligible skill provided in ServiceNow Otto applications in AI Skill Kit so that you can edit its prompt or change its AI service provider. Editing the prompt lets you control the format and content of the large language model (LLM) response.
          • Create a prompt -- After you create a custom skill, create a prompt. The prompt defines the instructions that the skill sends to the LLM and the skill inputs that it uses.
            • Add a tool -- Add and manage tools visually in the Tools editor, including decision branching, to execute different tools for your skill. Adding decision branches between tools enables you to define the conditions that must be met for a tool to run. If no conditions are met, the default branch's step is executed.
              • Add a retriever -- Add a retriever to your skill to augment your prompts with relevant context from AI Search results.
              • Add a web search -- Add a web search as a tool in AI Skill Kit to include web search results in your skill prompts.
              • Add Predictive Intelligence -- Add Predictive Intelligence as a tool in AI Skill Kit. Predictive Intelligence models predict values, estimate outcomes, and identify patterns that you can use to route work, populate forms, and estimate wait times.
              • Add Document Intelligence -- Add Document Intelligence as a tool in AI Skill Kit to extract structured data from documents as part of your skill's execution flow.
          • Use prompt assistance -- Use prompt assistance to start your prompt from an example in the prompt library or from a prompt that ServiceNow Otto generates.
          • Test a prompt -- After you create a prompt for your custom skill, test it before you finalize it to verify that it returns the expected results.
          • Evaluate a prompt -- Use the AI Skill Kit evaluation tools to measure how your skill prompts perform against a dataset, using automated metrics and human feedback.
          • Finalize and publish a skill -- Finalize at least one prompt and publish your custom skill so that a Otto admin can activate it.
          • Activate a skill -- After you create and publish a custom skill, you must activate it in AI Admin Hub. Activating the skill enables you to trigger the skill within the UI.
          • Call a custom skill from a script -- Call a custom skill from a UI action script so that you can run the skill and use its output in your instance logic.
        • AI Skill Kit reference -- Look up the roles, general guidelines, and log tables that support custom skill development in AI Skill Kit.
      • AI Admin Hub -- ServiceNow Otto uses generative AI to enhance user productivity and efficiency through conversation and proactive experiences. Starting with the Brazil release, AI Admin Hub is being prepared for deprecation and replacement by AI Admin Center.
        • Exploring AI Admin Hub -- With the AI Admin Hub application (formerly Now Assist Admin Console) you can activate, manage, and monitor AI skills and capabilities. Starting with the Brazil release, AI Admin Hub is being prepared for deprecation and replacement by AI Admin Center.
          • Overview tab in AI Admin Hub -- The Overview tab of the AI Admin Hub console provides information about available AI plugins and skills at a glance. Learn what skills are in use and what skills you can activate.
          • ServiceNow Otto Experiences -- Explore ServiceNow Otto panel and ServiceNow Otto context menu under the ServiceNow Otto Experiences tab of ServiceNow Otto Admin.
            • ServiceNow Otto panel -- With the ServiceNow Otto panel, you can get assistance from generative AI experiences to solve customer issues faster. Use this conversational interface to summarize a chat, case, or incident, get help, or generate resolution notes so that you can get the context of this information more quickly.
              • Standard chat -- With the ServiceNow Otto panel standard chat, you can get assistance from generative AI experiences to solve customer issues faster. Use this conversational interface to summarize a chat, case, or incident, get help, or generate resolution notes so that you can get the context of this information more quickly.
              • Enhanced chat -- ServiceNow Otto panel enhanced chat is a conversational support experience within a dynamic window that also includes the ability to have multiple active conversations and superior search capabilities. Use ServiceNow Otto panel enhanced chat to improve your productivity and efficiency by leveraging generative AI to perform tasks such as summarize a chat, case, or incident, request help, generate resolution notes, among others.
              • Premium chat -- ServiceNow Otto panel premium chat is an AI chat experience built into your ServiceNow environment. Ask questions, get answers from your organization's knowledge, and take action on records. It supports file uploads, web search, and multistep agentic tasks, so you can handle more complex requests without leaving the panel.
            • ServiceNow Otto context menu -- The ServiceNow Otto context menu uses generative AI to help agents summarize, create, and edit written content, thus streamlining their writing tasks.
          • Analyzing AI performance -- Use the AI Analytics dashboard to monitor the usage and performance of generative AI features and capabilities.
            • Exploring AI Analytics -- Learn how AI Analytics enables users with the AI Analytics Viewer or AI Analytics Admin role to monitor the usage, adoption, and performance of generative AI features and capabilities.
            • Configuring AI Analytics -- Configure the AI Analytics dashboard to view usage, value, and performance indicators for generative AI features on your instance.
              • Installing AI Analytics -- You can install the AI Analytics application (sn_na_analytics) with any of the ServiceNow Otto products if you have the admin role.
              • Map a skill to a dashboard -- Map an AI skill to a dashboard to view skill performance indicators and skill details.
            • Using AI Analytics -- The AI Analytics dashboard provides indicators and breakdowns that help monitor the performance of generative AI features, capabilities, and skills active on your instance.
              • Usage and adoption -- The Usage and adoption dashboard page contains key usage and performance indicators that help you evaluate AI adoption in your organization.
              • Skills performance -- Use the Skills performance dashboard page to view usage and performance indicators of active AI skills.
                • Skill details -- Use the Skill details dashboard page to view usage and performance indicators of a skill.
                • Custom skill details -- Use the Custom skill details dashboard page to view usage and performance indicators of custom skills.
              • AI Guardian analytics -- Monitor the performance of guardrails enabled through AI Guardian.
              • User search analyzer -- Gain insights into user search queries and AI-powered search results.
              • ServiceNow Otto context menu analytics -- Monitor the usage and performance of the ServiceNow Otto context menu.
            • AI Analytics reference -- AI Analytics reference topics include information about user roles and details of the indicators on the dashboard.
          • AI Admin Hub Settings -- Configure general settings for AI Admin Hub from the Settings tab.
            • Configure multilingual service for ServiceNow Otto applications -- Turn on multilingual service for user-entered text with native translation or Dynamic Translation in ServiceNow Otto applications.
            • Data sharing and processes -- Data sharing and processes topic description.
            • AI Guardian -- AI Guardian is built on the ServiceNow Small Language Model (SLM) and monitors generative AI interactions to detect offensive content, prompt injection attacks, and sensitive topics.
            • Manage AI models -- Access and select the LLM (large language model) provider used for various Now Assist skills. The selection impacts all the skills within the capability.
              • Manage model providers -- Edit or customize the model provider for a skill or skill group at the instance level from the list of supported third-party model providers, including the default Now LLM Service. You can also review the model policy set by your organization, and view the change history here.
              • Manage Integration -- Choose the preferred integration type for configuring the available model providers. There are two ways to configure a model provider in AI Admin Hub. You can either select Original Equipment Manufacturer (OEM) or Bring Your Own Key (BYOK).
              • Manage version -- Manage the version of the model providers across skills and instance levels. You can change and update versions for the out-of-box and custom skills.
            • Review your AI Admin Hub account -- Review your license details on the Account page of AI Admin Hub to make sure that you're up to date on what's available to you.
            • Usage alerts -- Define threshold-based rules at the skill levels to monitor and manage assist consumption and skill execution counts when limits are reached. The solution aims to prevent resource exhaustion, and provide clear, actionable insights through an alerts feed and a rule management interface.
              • Create alert rule -- Create alert rules to track the usage of generative AI skills in AI Admin Hub and notify you in the instance and via email, when the set thresholds are reached.
        • Configuring plugins and skills in AI Admin Hub -- Use AI Admin Hub to configure AI plugins and skills available to your organization. Starting with the Brazil release, AI Admin Hub is being prepared for deprecation and replacement by AI Admin Center.
          • Install AI plugins in AI Admin Hub -- Install plugins in AI Admin Hub to enable AI applications on your instance.
            • AI Suites -- The Application Manager uses AI Suites versions to verify compatibility between multiple generative AI applications in one instance.
              • Example -- The Application Manager uses AI Suites versions to verify compatibility between multiple generative AI applications in one instance.
          • Activate the ServiceNow Otto panel standard chat -- Activate the ServiceNow Otto panel standard chat to enable your agents to use AI skills, such as task summarization or navigation, in a side panel on the user interface.
          • Activate ServiceNow Otto panel enhanced chat -- Activate the ServiceNow Otto panel enhanced chat to enable your agents to use ServiceNow Otto skills, such as task summarization or navigation, in a side panel on the user interface.
          • Activate ServiceNow Otto panel assistants -- You must activate ServiceNow Otto panel assistants before using them.
          • Enable voice input for ServiceNow Otto panel -- Give users the option to use their voice when interacting with the ServiceNow Otto panel to make the panel more accessible. Voice input enables you to use the panel without needing to use a keyboard.
          • Configure disambiguation -- Configure the disambiguation property that controls when the assistant asks clarifying questions before responding to a ServiceNow Otto for Virtual Agent or ServiceNow Otto panel user request.
          • Configure response feedback -- Configure the response feedback options that appear when users select thumbs up or thumbs down on a ServiceNow Otto for Virtual Agent or ServiceNow Otto panel response.
          • Configure processing messages -- For ServiceNow Otto panel premium chat, configure processing messages to control the status updates that appear in the chat interface while ServiceNow Otto works on a request. You can customize the text of processing messages to better reflect your organization's terminology or the specific actions your AI agents perform.
        • Using AI Admin Hub -- Use AI Admin Hub to explore the AI plugins and skills available to you. Starting with the Brazil release, AI Admin Hub is being prepared for deprecation and replacement by AI Admin Center.
          • Activate an AI skill -- Activate AI skills by configuring settings such as display locations. After the skills have been activated, they can be used across the ServiceNow AI Platform based on the availability and display settings you choose.
          • Edit an AI skill -- Edit the configuration of an AI skill to choose the inputs or triggers and the display location of the skill output.
          • Make a copy of an AI skill -- Create a copy of an AI skill using the Make a copy function in AI Admin Hub. With a copy of the skill, you can experiment with skill settings and tailor the skill to fit your business needs.
          • Analyzing Now Assist usage -- Use the Now Assist analytics and monitoring tools in the Overview page to review the summaries, skill usage information, and issues that need your attention.
        • AI Admin Hub reference -- Reference topics include information about user roles, data usage, and domain separation for AI Admin Hub.
          • Default and target model version -- Model version is the large language model version a skill uses to route requests to process users' queries. Default model version is where all the requests route to by default. This is pre-set by ServiceNow. A target model version is chosen to route your requests to a different version at run-time, rather than using the default version.
          • Domain separation in the AI Admin Hub console -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.In the short description, edit the first sentence to state whether domain separation is supported or not and add the application name. Keep the conkeyref at the end that describes domain separation.Domain separation is supported for the AI Admin Hub console. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
          • Domain separation in ServiceNow Otto panel -- Domain separation is supported for ServiceNow Otto panel. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
          • Fetch end points in Now Assist Conversational Help skills -- The Now Assist Conversational Help skills architecture solves latency by fetching answers hosted at the nearest location, which is best suited to the user.
          • AI Admin Hub roles -- Certain roles are required to use AI Admin Hub functionality. The base admin (sys_admin) role does not automatically grant or include the following roles, so assign these directly to users who require them.
            • Now Assist Admin [sn_nowassist_admin.nsa_admin] -- Certain roles are required to use AI Admin Hub functionality. The base admin (sys_admin) role does not automatically grant or include the following roles, so assign these directly to users who require them.
            • AI Admin Hub console user [sn_nowassist_admin.user] -- Certain roles are required to use AI Admin Hub functionality. The base admin (sys_admin) role does not automatically grant or include the following roles, so assign these directly to users who require them.
            • ServiceNow Otto panel user [now_assist_panel_user] -- Certain roles are required to use AI Admin Hub functionality. The base admin (sys_admin) role does not automatically grant or include the following roles, so assign these directly to users who require them.
          • User data usage policy for Now Assist -- Now Assist is designed to keep user data safe and secure. You can also mask sensitive data or opt-out of sharing data for model improvements.
          • Troubleshoot an AI skill -- Run diagnostics for a skill on the AI Admin Hub console to get information about the status of your skill configuration. The availability of diagnostics depends on the skill.
          • ServiceNow Otto panel system properties -- Use system properties to customize ServiceNow Otto panel. Some properties are available on a system properties form, but some lesser-used properties are available only from the System Property [sys_properties] table.
      • Content Understanding -- Content Understanding uses AI to extract and summarize information from documents and images, so teams can act on results faster.
        • Explore -- Content Understanding brings generative AI to document and visual processing, so you can extract, analyze, summarize, and answer questions about the content in your files.
          • Benefits -- Content Understanding includes AI-powered skills and AI agents that extract, process, and summarize information from documents and images. Each capability delivers a distinct benefit for administrators and end users.
          • Information Extraction skill -- The Extract Information from documents skill (Information Extraction skill) uses generative AI to automatically extract content from documents and images, and to respond to questions about that content.
            • Extraction methods -- The Extract information from documents skill (Information Extraction skill) supports three extraction methods—field, table, and Q&A—each suited for different types of document data. Understanding which method to use helps you capture and store the right information in ServiceNow.
            • Predictions -- A prediction is the value that the Information Extraction skill infers for each field, table, or question in a use case. Predictions drive automation decisions and can be applied automatically or reviewed by a person, depending on the use case configuration.
            • Use cases -- Use cases in the Information Extraction skill define what documents to process and what information to extract, so generative AI can accurately retrieve structured data from unstructured documents.
            • Automation modes -- Automation modes in the Information Extraction skill determine whether predictions are accepted automatically or routed to a human agent for review before a document task completes.
            • Workflow -- Information Extraction is a skill that analyzes documents to provide values for defined fields, table columns, and questions in a use case. It populates ServiceNow records with extracted data from documents.
          • Attachment Summarization -- The attachment summarization skill summarizes a record's attachments alongside the record summary, so agents can review key content without opening each file.
          • Content insights AI agent -- The Content insights AI agent understands documents and images, answers questions, extracts structured data, and summarizes content within a single interface.
        • Configure -- Configure the capabilities in Content Understanding to extract, analyze, and answer questions about your document and visual content.
          • Information Extraction skill -- Configure the Extract information from documents skill (Information Extraction skill) to define how AI agents identify and pull structured data from unstructured sources. Use this configuration to control extraction behavior, map output fields, and integrate results into your workflows.
            • Activate the skill -- Activate the Information Extraction skill, so AI agents can analyze and extract information from documents using generative AI.
            • Set up a use case -- Create a use case to define the information to extract from a document for processing.
              • Test a use case -- Test a use case with a sample document to verify how well it extracts and processes information. Upload a document from a record or your device, then review the test outputs before saving your results.
              • Add integration -- Connect a use case to a workflow by adding an integration. Integrations automate document task creation or value extraction based on triggers in the target table.
              • Review and activate -- Review your configuration selections before completing the setup for a use case. Return to any previous step to make changes before finalizing.
            • Turn on full automation mode -- Turn on Full automation mode to automatically complete and submit document tasks without an agent review. Full automation mode is turned off by default in document extraction use cases.
            • Manage use case -- Administrators can manage an existing use case by changing the LLM, editing configuration details, creating a copy, deactivating, or deleting it.
              • Change the use case LLM -- Select the LLM and file language for a use case to control how documents are processed for information extraction. Change these settings when the default model doesn't suit your use case.
              • Copy a use case -- Copy an existing use case to use as a starting point for a similar one. The copy includes the original fields, tables, questions, integrations, and flows.
              • Edit a use case -- Update an existing use case to modify its name, fields, tables, questions, integrations, and flows. Use cases marked as read-only must be copied before you can edit them.
              • Deactivate a use case -- Deactivate a use case to stop it from being applied during document processing when it is no longer relevant to your document intelligence workflows.
              • Delete a use case -- Delete a use case and its associated fields, tables, questions, integrations, and flows from a skill when the use case is no longer needed.
          • Content insights AI agent -- Configure the Content Insights AI agent to control which roles can access it, how it is triggered, and which chat assistants surface it.
          • Attachment Summarization skill -- Configuring Attachment Summarization skill to automate key information extraction from documents.
        • Use -- Use Content Understanding to process and extract meaning from unstructured content in your ServiceNow instance. This section provides an overview of the workflow and links to the tasks required to complete the process.
          • Information Extraction skill -- The Information Extraction skill generates predictions from activated use cases. In agent review mode, you review and correct predictions before the extracted values populate your records.
            • Review predictions -- After a use case is activated in agent review mode, you can review the predictions generated by the Information Extraction skill and, if needed, modify them before submitting.
          • Content insights AI agent -- Use the Content Insights AI agent to generate information from your inputs, attached documents, or images
            • Question and answer -- Use question and answer (QnA) to ask the Content Insights AI agent specific questions about document or image and get cited answers. QnA is the agent's default mode.
            • Key information extraction -- Use key information extraction (KIE) to extract structured data from documents with a predefined template, for processing standardized documents such as invoices, contracts, or forms.
            • Document summarization -- Use the Content Insights AI agent to generate a concise summary of document or image from a record reference or uploaded attachment.
        • Reference -- Reference topics provide additional information about the lists and forms that you use to configure and administer Content Understanding.
          • Personas -- Personas define the roles that interact with Content Understanding and the actions each role performs.
          • Supported languages -- Use this reference to identify which languages the Content Understanding application supports for text-based and image-based files, and which optical character recognition (OCR) model applies to each language group.
          • LLMs -- The Content Understanding application uses large language models (LLMs) to support generative AI and agentic AI capabilities.
          • Forms -- Reference forms provide fields for viewing and updating Content Understanding records, including fields, questions, and tables.
            • Field form -- The field form defines the information to extract from a document, including the field name, type, and target table.
            • Question form -- The Question form contains fields that define a question and how its answer is extracted from a document in a use case.
            • Table form -- The Table form contains fields for defining a table and its columns for document extraction in a use case.
          • Field types -- Field types determine what kind of information is extracted from a document and how that information is stored or displayed in a use case.
          • Integrations -- Content Understanding integrates with ServiceNow solutions to extract, analyze, and summarize information documents.
          • Data normalization -- Data extracted from documents is converted into a standard format. This ensures that values appear consistently across all fields, making the data easier to group, analyze, and integrate with other applications.
          • Limitations -- Review the file format, size, page count, and language limitations that apply to skills and AI agents in Content Understanding.
      • ServiceNow AI Lens -- With ServiceNow AI Lens, which is a ServiceNow AI application, you can use generative AI to scan, extract, comprehend, and synthesize data to optimize your workflows.
        • Explore -- ServiceNow AI Lens is a ServiceNow AI application that uses generative AI to scan images and screens, extract information, understand visual data, and take action—such as automatically filling in forms with scanned information—to help improve your workflows.
          • ServiceNow AI Lens features -- Learn about the various ServiceNow AI Lens features to help you get started with analyzing and gathering insights from the visual data.
          • Desktop app landing page overview -- Learn about the ServiceNow AI Lens desktop application landing page.
          • Supporting information -- Get a quick overview of the important information that is related to the ServiceNow AI Lens application.
          • ServiceNow AI Lens skill -- This skill provides generative AI capabilities to read, understand, respond, and act on visual data such as hand-written texts, images, and websites and take powerful actions to boost productivity.
        • Configure -- If you have the admin role, you can enable the ServiceNow AI Lens application (sn_ai_lens) to extract and comprehend data for various workflows.
        • Use -- If you have a lens_user role, and have activated the ServiceNow AI Lens skill, you can use the ServiceNow AI Lens application to capture screens or upload files, extract and comprehend data from the captured screenshots or uploaded files, auto-fill form fields, or preview the extracted data.
          • Create or update a record in an instance -- Create or update a record in the ServiceNow instance by auto-filling the form fields with data that ServiceNow AI Lens extracts from screens and files.
            • Using the Lens browser app -- Create or update a record in the ServiceNow instance by auto-filling the form fields with data that ServiceNow AI Lens extracts from screens and files.
            • Using the Lens desktop app -- Create or update a record in the ServiceNow instance by auto-filling the form fields with data that ServiceNow AI Lens extracts from screens and files.
          • Auto-fill catalog item form in the Service Portal -- Use ServiceNow AI Lens to extract data from documents and auto-fill catalog item forms in Service Portal. For example, auto-fill a new vendor onboarding form by extracting key details such as vendor name, address, contact email, and banking information from multiple documents, that includes Excel files, emails, images, and PDF documents.
            • Using the Lens browser app -- Use ServiceNow AI Lens to extract data from documents and auto-fill catalog item forms in Service Portal. For example, auto-fill a new vendor onboarding form by extracting key details such as vendor name, address, contact email, and banking information from multiple documents, that includes Excel files, emails, images, and PDF documents.
            • Using the Lens desktop app -- Use ServiceNow AI Lens to extract data from documents and auto-fill catalog item forms in Service Portal. For example, auto-fill a new vendor onboarding form by extracting key details such as vendor name, address, contact email, and banking information from multiple documents, that includes Excel files, emails, images, and PDF documents.
          • Trigger ServiceNow AI Lens from the desktop app -- Trigger ServiceNow AI Lens from the desktop app by using a Lens action to preview the extracted data and initiate post processing or auto-fill a form.
          • Extract and analyze data with ServiceNow AI Lens desktop app -- Extract and analyze data from one or more screenshots that you capture or files that you upload, and then preview the data analysis.
          • Extract and analyze data with ServiceNow AI Lens in Virtual Agent -- Extract and analyze data from an image using ServiceNow AI Lens from a Virtual Agent conversation on a mobile device or a portal. ServiceNow AI Lens can scan an image and then gather insights or provide recommendations as per your instructions.
        • Reference -- Reference topics provide additional information about the roles and tables that are installed with the ServiceNow AI Lens application.
    • AI agents and agentic workflows -- Design, deploy, and evaluate AI agents and agentic workflows that autonomously complete multi-step tasks on the ServiceNow AI Platform.
      • AI agents library -- All ServiceNow AI agents are listed. Depending on your license, not all AI agents may appear in your instance.
        • Accounts Payable Operations AI agents -- The following AI agents are available for Accounts Payable Operations.
          • Inquiry resolution provider AI agent -- This AI agent assists with invoice inquiries by providing resolution details based on the invoice and its related data. It is intended for use by Accounts Payable Operations agents handling invoice inquiries.
          • Recommend invoice owner AI agent -- This AI agent analyzes exception work notes to predict the most likely business owner for an invoice. It works with the Accounts Payable (AP) specialist by suggesting the predicted owner or creating follow-up tasks to validate and resolve ownership.
          • Email parser agent -- This AI agent identifies and classifies actionable requests, and routes them to the appropriate workflows to create invoice cases.
          • Zero touch service desk agent -- This AI agent investigates supplier invoice inquiry cases and generates a response for the supplier contact. Fulfillers can review its work in the Agentic Processes panel on the case.
        • AIOps and Leap AI agents -- The following AI agents are available for AIOps and AIOps Leap.
          • Alert automation AI agent -- This agent interprets free-text user requests related to alert automation and guides users to the appropriate automation experience. It detects whether the user intends to enrich alerts, group alerts, respond to alerts, or any combination of these actions.
          • Alert impact verification AI agent -- This agent is responsible for eligibility validation for a given alert, to perform impact analysis on it.
          • Artifact creation agent AI agent -- Assists in creating and viewing artifacts such as problem records, knowledge base articles, and playbooks for an automation opportunity. The agent checks for an automation opportunity number and invokes the artifact creation topic tool to generate the required artifacts.
          • Business and technology management service impact analysis AI agent -- This agent calculates the business and technology management services impacted by a given alert.
          • Manage alerts AI agent -- Responsible for generating reports for a given alert and storing a structured summary with key insights and recommended next steps in the alert record.
          • Service instance impact analysis AI agent -- This agent performs alert impact analysis on service instances for a given alert.
          • User impact analysis AI Agent -- This agent investigates incidents and cases related to the alerts and affected services.
          • Artifact creation agent AI agent -- The Artifact creation agent helps users create and view artifacts for an automation opportunity, such as a problem record, a knowledge base article, or a playbook.
          • LEAP Ansible Agent AI agent -- The LEAP Ansible agent finds the Ansible job template that best matches the problem behind an automation opportunity. It recommends the template to the user and saves it to the discovered job catalog.
          • LEAP Ansible Execution Agent AI agent -- The LEAP Ansible Execution agent runs the Ansible playbooks mapped to each resolution step of an incident. It launches jobs through Ansible Automation Platform, prompts the user to complete unmapped steps manually, and reports job status on request.
          • LEAP KB Creation Agent AI agent -- The LEAP KB Creation agent creates draft knowledge base articles from the resolution steps of a LEAP automation opportunity.
          • LEAP Problem Creation Agent AI agent -- The LEAP Problem Creation agent creates problem records from the data of a LEAP automation opportunity.
        • AI Search AI agents -- The following AI agents are available for AI Search.
          • AI Search Configuration AI agent -- Responsible for managing the end-to-end process of formally configuring AI Search for ServiceNow internal tables. This agent is invoked whenever a user mentions ServiceNow internal tables in the context of AI Search.
        • AI Workflow Factory Prime AI agents -- The following AI agents are available for AI Workflow Factory Prime.
          • Autonomous Engineer -- This AI agent helps with implementing ServiceNow applications. The agent accepts requirements, generates a plan with structured work items, and builds all work items in parallel using background AI agents.
        • Asset Management AI agents -- The following AI agents are available for Asset Management.
          • Asset next best action AI agent -- This AI agent validates task numbers, identifies task types, and routes workflows to the correct specialized agent for troubleshooting or repair. It processes one task at a time for accurate handling of hardware asset repair order tasks.
          • Asset sourcing AI agent -- This AI agent helps source a requested item by generating and executing sourcing plans through consumption, transfer, and purchase. The agent creates plans autonomously or with user guidance, coordinates with external agents for transfer and purchase orders, and validates sourcing status throughout the process.
          • Evaluate asset AI agent -- This AI agent helps troubleshoot asset-related issues using the Web Search tool. It guides users to select a resolution and completes the troubleshooting task on confirmation.
          • Purchase order creation AI agent -- This AI agent is used to create a purchase order.
          • Repair asset AI agent -- This AI agent assists users in resolving issues with assets that are in a defective or pending repair state. It specializes in identifying and suggesting appropriate repair steps by leveraging the Web Search tool. The agent guides users through the repair process, helps them select a suitable resolution, and automatically updates and completes the repair task upon confirmation.
          • Transfer order creation AI agent -- This AI agent is used for creating a transfer order to source a requested item.
        • Care Team Operations AI agents -- The following AI agents are available for Care Team Operations.
          • Care Team Operations case creation AI agent -- This AI agent streamlines case creation by analyzing user conversations to accurately determine the service definition for each reported issue. It intelligently identifies multiple issues raised in a single conversation and creates separate cases with correct case type and service definition.
          • Care Team Operations case creation AI voice agent -- This agent helps healthcare staff report and submit Care Team Operations (CTO) requests. Trigger this agent when a user mentions Care Team Operations, CTO, or asks to submit a care team request.
          • Care Team Operations case intake AI agent -- This workflow guides users through submitting operational issues by prompting for a clear problem description and ensuring required details—such as location, requesting unit, asset tag, and priority—are captured. It intelligently detects and separates multiple requests in a single user utterance, summarizes each request with its details, and confirms accuracy with the user before proceeding.
        • CMDB AI agents -- The following AI agents are available for CMDB.
        • Contract Management Pro AI agents -- The following AI agents are available for Contract Management Pro.
          • Contract repository AI agent -- This AI agent retrieves contract repository details for a specified record, including vendor information, contract model, and document attachment IDs. It also calculates the average lead time for similar contracts when vendor, supplier, or account data exists.
          • Search contracts AI agent -- This AI agent helps legal professionals, procurement teams, sales executives, and compliance officers find and understand legal contracts through conversational search and Q&A. It classifies each query, retrieves matching contract metadata or content, and links directly to results, while declining requests to draft, modify, or legally interpret contracts.
        • Core Business Suite AI agents -- The following AI agents are available for Core Business Suite.
          • CBS Bulk Upload AI Agent -- The CBS Bulk Upload AI agent handles bulk record creation and updates for the Space, Supplier, and Supplier Contact tables.
        • Customer Service Management AI agents -- The following AI agents are available for Customer Service Management.
          • Case action AI agent -- This agent can preform actions for the customer, including case actions (Create a case task, Update work notes, etc.) and more.
          • Case creation AI agent -- The Case creation AI agent is designed to automate and manage the end-to-end process of case creation. This agent should be invoked when a case needs to be created.
          • Case status AI voice agent -- This AI agent helps users quickly retrieve and understand the status of their cases through a conversational voice interface.
          • Complaint case research plan AI agent -- Analyzes "Under Review" complaint cases to identify previously attempted troubleshooting steps and recommends new solutions from similar closed cases and knowledge articles. Prioritizes relevant suggestions, presents them with source attribution, updates work notes, and creates case task plans based on successful resolution patterns. Filters redundant recommendations and ensures proper workflow integration within case management systems.
          • Complaint case triage AI agent -- This agent is designed to analyze complaint cases after their creation, automatically deriving key classification and prioritization fields. It serves case handlers and support teams by providing reliable, data-driven insights to enhance case management efficiency.
          • Context validator AI agent -- The context validator AI agent is designed to validate the record, analyze the sentiment, and get the list of intents from the input record. This agent should be invoked when the record content needs to be validated.
          • Create case AI voice agent -- This voice agent enables users to log cases using voice input. It guides the user through a structured conversation to capture and validate all mandatory case details, creates the case record, and provides confirmation upon successful submission.
          • Customer insight AI agent -- This agent is responsible for answering any questions related to the record. The information it can retrieve includes customer information (name, contact info, details, location, history, cases, and orders) and case information (next steps, actions, agent, notes, documents, tasks, and resolutions).
          • Document verification AI agent -- The document verification AI agent verifies the documents on a record to determine if they match the documents listed for the case type. Additionally, they determine if any documents are missing or if document verification has failed. This agent should be invoked when documents need to be verified.
          • Duplicate identification AI agent -- The duplicate identification AI agent identifies duplicate records.
          • Email response AI agent -- The email response AI agent generates and sends an email response.
          • Entity extraction AI agent -- The entity extraction AI agent extracts entities from emails and information from documents. It matches the entities with a list of approved fields.
          • Image to task plan template AI agent -- This AI agent asks the user to upload an image, extracts the task dependencies from it, and returns the result as JSON.
          • Informational queries AI agent -- The informational queries AI agent summarizes all informational answers for a record.
          • Issue identifier complaint case intake AI agent -- This AI agent is used for product and location-based grievances. It helps with intakes, documentation, and processing.
          • Live interaction recommendations AI agent -- The AI agent analyzes the conversation between a customer and a human agent. It recommends actions that help a human agent resolve the customer's issue.
          • RMA Assistant AI agent -- This AI agent helps customers and human agents with RMA case creation and processing for product returns, repairs, and replacements.
          • Transactional queries AI agent -- The transactional queries AI agent will update a record with any collected transactional values.
          • Triage cases planner AI agent -- This AI agent triages cases. It takes appropriate actions based on the record's sentiment and intents. It is intended for agents and end-users who need assistance in resolving queries efficiently, as well as assessing a record for possible case creation.
          • Triage cases wrap up AI agent -- The triage cases wrap up AI agent finalizes the case triage process by synthesizing the execution and posting the summary to the record’s work notes.
          • Troubleshooting steps identification AI agent -- An AI agent responsible for gathering required context, identifying troubleshooting steps by comparing with KBs, similar cases and standard operating manuals, and proposing additional troubleshooting steps.
        • Employee Experience AI agents -- The following AI agents are available for Employee Experience.
        • Employee Service Management AI agents -- The following AI agents are available for Employee Service Management.
          • Universal Request departmental ticket creator AI agent -- Automates the routing of universal requests to appropriate departmental ticketing systems by analyzing department predictions and creating properly configured HR cases or IT incidents with all necessary field mappings and reference tracking.
        • Enterprise Architecture AI agents -- The following AI agents are available for Enterprise Architecture.
          • Enterprise Architecture explorer for analysis and queries AI agent -- The agent answers questions about Enterprise Architecture data based on Common Service Data Model (CSDM) 5.0 entities and their relationships. It covers business capabilities, business applications, services, infrastructure, integrations, value streams, AI systems, technology standards, and conformance.
          • Enterprise Architecture diagrams AI agent -- The agent finds a business application by name or ID and generates a hierarchy diagram saved as a named architectural artifact. The agent also summarizes the generated diagram.
        • Field Service Management AI agents -- The following AI agents are available for Field Service Management.
          • Create work order AI agent -- This AI agent creates work orders using text descriptions and image.
          • Parts audit AI agent -- This AI agent assists technicians in conducting thorough parts validation only for work order tasks. It streamlines the process of verifying and reporting parts usage, ensuring accuracy and accountability.
          • Shift and schedule management AI agent -- This AI agent helps managers create, review, update, and delete shifts and schedules, and assign technicians to them. It suggests default shift details, finds technicians by skill or name, and asks the manager to confirm one complete plan before making changes. Managers can also open shifts for technician signup.
        • Financial Services Operations AI Agents -- The following AI agents are available for Financial Services Operations.
          • ACH dispute return recommendation AI agent -- The AI agent guides the human agent through a structured decision-making process to determine the best action for an ACH dispute return task. The ACH dispute return recommendation AI agent analyzes disputed transactions based on merchant analysis and Nacha eligibility. The agent recommends actions based on historical data, and applies predefined rules when data is limited.
          • Banking CSR customer insights AI agent -- The AI agent answers a customer service representative's questions about a banking customer, presenting account, transaction, and case information in a clear, structured format so the representative can quickly explore relevant customer data.
          • Banking CSR support AI agent -- The AI agent acts as a copilot for a customer service representative on a live banking call or chat, retrieving account, transaction, balance, credit, loan, and policy information in real time and presenting it in a clear, conversational format so the representative can respond quickly.
          • Dispute communication AI agent -- The agent drafts a customer email about a card dispute outcome. It chooses the message template based on the dispute's final action, fills in the relevant transaction and merchant details, and adjusts the tone to match the template's intended message.
          • Friendly fraud AI agent -- The agent guides the human agent through resolving a friendly fraud dispute. It recommends an action based on published guidance and similar past overrides, then supports the agent's decision with real-time context to keep resolutions accurate and compliant.
          • Insurance CSR customer insights AI agent -- The agent acts as a copilot for a customer service representative (CSR), answering natural-language questions about a single customer's insurance policies, coverages, claims, billing, and servicing cases, as well as general product and procedural guidance, and presents structured, context-aware answers with follow-up options.
          • Insurance CSR support AI agent -- The agent gives a customer service representative (CSR) real-time answers during a live insurance call, either from a typed question or from the latest call transcript, retrieving the customer's policy, coverage, claim, and billing data or knowledge-base guidance so the CSR can respond quickly without switching screens.
          • Merchant analysis for disputes AI agent -- The agent evaluates the merchant behind a disputed transaction for credibility. It researches the merchant's reputation and regulatory history, weighs the evidence against a set of rules, and recommends whether the merchant is credible, with a rationale the human agent can accept or override.
          • Nacha operating guidelines check AI agent -- The agent determines whether a return code assigned to a disputed transaction is eligible for filing. It checks the case against NACHA operating guidelines' time-frame and documentation requirements and presents its eligibility decision and reasoning to the human agent for confirmation.
        • Governance, Risk, and Compliance AI agents -- The following AI agents are available for Governance, Risk, and Compliance.
          • Control objective change AI agent -- This AI agent acts as a Compliance Manager that validates if the description and supplemental guidance of a given control objective need updates based on the associated citations. The AI agent recommends new values if changes are required, and updates the control objective record after getting confirmation from the user.
          • Issue action plan AI agent -- This AI agent identifies the optimal steps for resolving an issue by referencing the past similar issue details. It presents a step-by-step summarized action plan to the user.
          • Remediation tasks AI agent -- This AI agent identifies the remediation tasks for resolving an issue by referencing the action plan field on the issue record.
          • Report a GRC issue AI agent -- This AI agent enriches the given issue description with additional information by looking at historical data and using GRC context. It analyzes, extracts key information (such as issue type, date of occurrence, and so on), and creates a GRC issue.
          • Risk Suggestion AI agent -- The Risk Suggestion AI agent builds context for an entity and suggests relevant risks for it. It draws on your internal risk library, model-driven inference, and, with your permission, external public sources, and then creates the confirmed risks as triage records.
        • Hardware Asset Management AI agents -- The following AI agents are available for Hardware Asset Management.
        • Impact AI agents -- The following AI agents are available for Impact.
          • Code fix AI agent -- This AI Agent automates the process of analyzing, suggesting, and implementing fixes for code violations or issues detected within code repositories or running scripts. It leverages LLM-driven suggestions while keeping the user in control of approval and refinement.
        • Integration Hub AI agents -- The following AI agents are available for Integration Hub.
        • IT Operations Management AI agents -- The following AI agents are available for IT Operations Management.
          • Analyze potential impact AI agent -- This agent analyzes the potential business and operational impact of a proposed change by identifying affected servers and services. The agent reviews the change request, performs impact analysis, and documents findings in work notes to support informed decision-making and effective mitigation strategies.
          • AWS CloudWatch API AI agent -- This AI agent investigates AWS CloudWatch alarm firings end to end by querying alarm configuration, metric time series, log groups, ML anomaly detectors, and Logs Insights. It then synthesizes findings into a structured root cause analysis report with metric analysis, log evidence, and correlated service impact.
          • AWS CloudWatch MCP server AI agent -- This AI agent automates AWS CloudWatch alert investigations by analyzing alarm details, querying affected resources, and retrieving CloudWatch metrics and logs across multiple strategies. It provides clear summaries with root cause analysis and actionable recommendations for resolution.
          • Azure Monitor MCP AI agent -- This AI agent investigates Azure Monitor alerts by querying Log Analytics workspaces with KQL, retrieving platform metrics, and checking activity logs and resource health through Azure MCP tools. It returns structured findings to the parent agent.
          • CSDM business application to infrastructure AI specialist -- This AI specialist finds the best matching discovered service for each business application and creates the standard CSDM "Uses::Used by" relationship in the CI relationships table [cmdb_rel_ci].
          • Datadog APM MCP server AI agent -- This AI agent queries Datadog APM observability data using the full suite of Datadog MCP server tools. It can answer questions about service health, distributed traces, triggered monitors, log analysis, incidents, SLO compliance, deployment events, and service dependencies.
          • Dynatrace MCP server AI agent -- This agent investigates Dynatrace alerts by retrieving alert impact summaries and querying the Dynatrace API for problem details, entity enrichment, log analysis, and root cause theories.
          • Gemini Cloud Assist A2A investigation AI agent -- This AI agent investigates Google Cloud alerts by driving a Gemini Cloud Assist investigation through Google's A2A investigation endpoint. It starts an investigation, polls task status, and retrieves the structured investigation result with root-cause hypotheses and next steps.
          • Kentik analysis AI agent -- This AI agent fetches the incident insights report for a Kentik alert.
          • LogicMonitor API AI agent -- This AI agent investigates LogicMonitor alerts and monitored entities, assesses entity health, and recommends next steps.
          • Network SME AI agent -- This AI agent investigates network issues and recommends next steps.
          • New Relic MCP server AI agent -- This AI agent queries and interprets observability data from New Relic using the full suite of New Relic MCP server tools.
          • Prometheus API AI agent -- This AI agent analyzes and investigates Prometheus alerts and answers general Prometheus questions, surfacing infrastructure metrics through instant and range queries.
          • Service map AI agent -- This AI agent runs automatically on a schedule and creates service maps from ML-based and tag-based candidates.
          • SolarWinds analysis AI agent -- This AI agent fetches the details related to a SolarWinds alert by executing SWQL queries against SolarWinds.
          • Splunk MCP server AI agent -- This AI agent investigates Splunk Cloud and compatible Splunk Enterprise alerts by querying Splunk platform data. It doesn't cover Splunk Observability Cloud.
          • SRE investigate AI agent -- This AI agent coordinates investigation activities across multiple observability platforms by orchestrating tool-specific agents. It correlates findings, identifies probable root causes, and synthesizes comprehensive investigation reports.
          • ThousandEyes MCP server AI agent -- This AI agent investigates ThousandEyes tests by analyzing metrics, anomalies, network events, and outages. It returns probable causes and recommended next steps.
          • Pattern Diagnostic AI agent -- The Pattern Diagnostic Agent AI agent analyzes CMDB configuration item (CI) data quality by using Discovery pattern metadata. The agent identifies CIs with missing attribute values, parses discovery logs to diagnose the failures, and prepares the error data for remediation through the Error Framework.
        • IT Service Management AI agents -- The following AI agents are available for IT Service Management.
          • Additional incident context AI agent -- This AI agent retrieves information beyond the incident itself and presents the output in a readable format. This agent is strictly read-only; it can only retrieve and present information. It cannot update, modify, or perform any write operations on any records (such as adding comments, changing fields, reassigning, resolving, or closing incidents).
          • Agent client collector (ACC) diagnostic AI agent -- This agent assists users in resolving ACC errors by providing suggestions based on the error codes found in the ACC Error Reports. It aims to help users resolve errors efficiently and effectively.
          • Categorize ITSM incident AI agent -- This AI agent assigns the appropriate category and subcategory to an incident.
          • Create change request AI agent (autonomous) -- This AI agent creates structured change requests from conversational input by autonomously selecting the appropriate change model and template.
          • Change CI suggestion AI agent -- This AI agent recommends a list of relevant configuration items (CIs) that can be added as Affected CIs to the current change request.
          • Change CI suggestion AI agent (latest) -- This AI agent autonomously identifies and populates both the primary configuration item (CI) and affected configuration items on a change request without requiring multiple user interactions.
          • Change conflict assessor AI agent -- This AI agent can assess conflicts for changes. This includes checking mandatory fields and trigger conflict detection, and updating worknotes.
          • Change outage assistant AI agent -- This AI agent creates outage records for the change request based on the impacted CIs.
          • Change quality assessor AI agent -- This AI agent provides suggestions to improve inputs for a change form.
          • Change request plans AI agent -- This AI agent helps change owners and approvers by drafting high-quality, context-aware change request content.
          • Change request plans AI agent (autonomous) -- This AI agent autonomously drafts change plan fields during the readiness phase. Field population is governed by a resolved change policy to ensure consistent behavior without requiring user input.
          • Change template suggestion AI agent (autonomous) -- This AI agent identifies the most relevant change template and model for new change requests by analyzing request details and comparing them against available templates and historical data.
          • Classify service and CI AI agent -- This AI agent assigns the appropriate service and offering to an incident. It can also assign the appropriate configuration item.
          • Create incident AI agent -- Use this AI agent to log IT support requests. It responds to requests such as "create an incident," "raise an incident," "open an IT ticket," or "raise an IT support ticket."
            • Use the Create incident AI agent -- Use this AI agent to log IT support requests. It responds to requests such as "create an incident," "raise an incident," "open an IT ticket," or "raise an IT support ticket."
          • Create incident AI voice agent -- This AI agent creates new incidents when the user explicitly mentions they want to create a new incident or report a new issue.
          • DEX diagnosis AI agent -- This AI agent specializes in structured root cause diagnosis of device and application performance issues through a step-by-step process. This agent aggregates device health metrics, event logs and historical incident data, then systematically evaluates each source to isolate relevant evidence.
          • DEX remediation trigger AI agent -- This AI agent receives a resolution plan, checks for remedial actions, and executes the supported ones on end-user devices (Windows OS and MacOS endpoints) to resolve common device and application issues. Remedial actions are concrete, executable fix steps such as restarting services, clearing cache, or cleaning up temporary files.
          • DEX resolution plan AI agent -- This AI agent generates a resolution plan for the given issue based strictly on the root cause provided. The agent ensures all suggested steps are evidence-based, actionable, and aligned with the diagnosed root cause. No resolution is proposed outside these defined sources.
          • Incident category configuration AI agent -- This AI agent orchestrates the complete lifecycle of incident category and subcategory configuration for the Choices [sys_choice] table. It supports three interaction modes: guided conversation, file upload (CSV/XLSX), and industry-based recommendations.
          • Incident context AI agent -- This AI agent helps users answer questions related to a given incident using information from the incident record and its related records. This agent is strictly read-only — it can only retrieve and present information.
          • Incident knowledge article AI agent -- This AI agent can resolve incidents by finding existing similar knowledge articles and attaching them to the incident. It can also create a knowledge article for the incident.
          • Incident known error article AI agent -- This AI agent can find similar known error articles for an incident and attach them to the incident. It can also resolve the incident.
          • Incident resolution details AI agent -- This AI agent suggests resolution notes for an incident.
          • Incident routing configuration AI agent -- This AI agent creates, modifies, and deactivates assignment rules for incident routing.
          • ITSM incident resolution plan investigation AI agent -- This AI agent gets incident details, reviews similar incidents and knowledge articles, and then generates an incident resolution plan.
          • Link major incident or problem AI Agent -- This AI agent automatically identifies and links the most relevant major incident or problem with an incident.
          • Manage ticket AI voice agent -- This AI voice agent assists users with managing their active incidents and requested items.
          • Microsoft 365 group membership AI agent -- The agent helps users add or remove members of Microsoft 365 distribution list groups. It finds the group, validates the people to add or remove, confirms the action with the user, and records the request in an incident.
          • Password reset AI voice agent -- This AI voice agent helps users reset their password during phone-based interactions.
          • Post incident review AI agent -- This AI agent generates a post-incident review report for the user to review and revise after a major incident report.
          • Request catalog item AI voice agent -- This AI voice agent assists users in finding and delivering catalog items. If the item is not categorized as software, then the catalog link is sent through approved channels such as email or SMS. If the item is software, this agent will help create the request.
          • Schedule change request AI agent -- This AI agent schedules a change request.
          • Standard change template proposal AI agent -- Provided with a change request, this AI agent searches for similar changes and returns a list of similar changes to use for a proposal record.
          • Standard change template recommender AI agent -- This AI agent helps users create and submit change requests. Invoke it whenever the user asks to log, create, submit, initiate, or help with a change record of any type (standard, routine, scheduled, maintenance, infrastructure, software, database, security, or any changes specific to IT service management).
          • Submit account unlock catalog AI voice agent -- This AI voice agent helps users unlock accounts by invoking a tool call to submit an account-unlock catalog request.
          • Troubleshoot Outlook issue AI voice agent -- This AI voice agent troubleshoots Microsoft Outlook issues. It also sends a troubleshooting article link to the user by email when requested.
        • Legal Service Delivery AI agents -- The following AI agents are available for Legal Service Delivery.
        • Operational Sustainability Management AI agents -- The following AI agents are available for Operational Sustainability Management.
          • Calculation creation AI agent -- This AI agent creates a calculated metric definition record using the formula passed in the input.
          • Calculation operand AI agent -- This AI agent identifies and returns relevant metric definitions and emission factors from existing sources. It replaces generic references with precise metric definitions and emission factor names in the input formula.
        • Operational Technology Manager AI agents -- The following AI agents are available for Operational Technology Manager.
          • OT Excel import task AI agent -- The OT Excel import task AI agent imports Operational Technology (OT) device data from a spreadsheet into the Configuration Management Database (CMDB). The agent validates the imported records, creates remediation tasks for invalid records, and imports the valid records.
        • Operational Technology Service Management AI agents -- The following AI agents are available for Operational Technology Service Management.
        • Retail AI agents -- The following AI agents are available for Retail.
          • Store Inquiry AI Agent -- The agent resolves retail store inquiries by finding the most relevant solution in similar cases, knowledge articles, and documents. It presents the best match with its source and, based on the user's choice, updates the case.
        • Sales CRM AI agents -- The following AI agents are available for Sales Customer Relationship Management (Sales CRM).
          • Sales Automation AI agents -- The following AI agents are available for Sales Automation.
            • Lead outreach AI agent -- This AI agent sends outreach and follow-up emails to new leads on behalf of sales agents. It selects the email template based on how many emails the lead has already received, and disqualifies the lead when three emails go unanswered.
            • Appointment management AI agent -- This AI agent manages appointments with leads on behalf of sales agents. It reads lead emails, checks the lead owner's availability, and either books an appointment or proposes two open time slots. It also cancels appointments when a lead asks and sends a confirmation email.
            • Lead disinterest AI agent -- This AI agent handles lead disqualification and opt-out requests for sales agents. After the sales agent confirms, it cancels the lead's upcoming appointments, closes the related tasks, and disqualifies the lead.
            • Inbound email AI agent -- This AI agent analyzes the latest email that a lead sends in response to outreach and helps sales agents decide how to move forward. It classifies the response and then books a demo, disqualifies the lead, cancels the appointment, or drafts answers to the lead's questions.
            • Opportunity AI agent -- This AI agent helps the user read, create, update, and summarize opportunities and their related records, such as accounts, contacts, touchpoints, opportunity tasks, line items, and meetings. It previews changes to opportunities, accounts, contacts, and line items and makes them only after the user approves.
          • Order Management AI agents -- The following AI agents are available for Order Management.
            • Move order voice AI agent -- This Sales Customer Relationship Management voice agent helps users relocate a telecom service to a new address by validating the consumer, verifying serviceability at the target location, and creating a move order.
            • Order enrichment AI agent -- This Sales Customer Relationship Management agent identifies enrichment tasks for order line items and their children using historic data, confirms the task list with the user, and creates them.
            • Order fallout AI Agent -- This Sales Customer Relationship Management agent analyzes order task comments and work notes to detect issues matching known fallout types, creates fallout records for any matches, and summarizes the results.
            • Order fulfillment AI agent -- This Sales Customer Relationship Management agent identifies fulfillment tasks for a domain order by checking historic tasks from similar orders, confirms the task list with the user, and creates them.
            • Invoice dispute AI voice agent -- This AI voice agent helps customers resolve discrepancies between invoiced quantities and received quantities by creating dispute cases.
            • Invoice dispute intake assistant AI agent -- This AI agent helps requesters identify the correct invoice, confirm dispute details, and submit invoice disputes related to quantity issues. It guides users step by step through invoice identification, validation, and dispute submission to ensure a smooth and accurate experience. The agent also analyzes the sentiment of the user throughout the conversation.
            • Invoice dispute support assistant AI agent -- This agent helps users efficiently identify, review, and answer questions related to invoice disputes. It validates information, maintains data integrity, and answers questions regarding the invoice case.
            • Manage order operations AI agent -- This AI agent helps customers change an order by requesting faster delivery, increasing quantities, changing the shipping address, or combining these changes. The agent checks inventory, delivery, and pricing, then resolves the case within a price threshold, creates a quote, or hands off to a specialist.
            • Order capture AI agent -- The Order capture AI agent helps you create orders from quote lines or uploaded files, and manage, investigate, and update existing orders. For example, you can apply discounts, change quantities, fix shipping addresses, remove lines, create cases, and undo changes.
            • Order exception AI voice agent -- This AI voice agent helps customers change an order after they place it. Customers can request faster delivery, a higher quantity, or a different shipping location, in any combination, for one order line. The agent creates one case for the requested changes and can connect the customer to a live agent.
            • Telco order fulfilment template creation AI agent -- This Sales Customer Relationship Management AI agent generates a task plan template using the provided specification and dependency JSON.
          • CPQ AI agents -- The following AI agents are available for Configure, Price, Quote (CPQ).
            • Quote AI agent -- This AI agent helps sales agents create, update, and finalize quotes. It validates products against the catalog, adds and configures line items, applies discounts, and generates the quote document. When started from an opportunity, it reads the opportunity line items and notes to build the quote without manual input.
          • PRM AI agents -- The following AI agents are available for Partner Relationship Management (PRM).
            • Deal Registration AI agent -- Manages the end-to-end deal registration workflow. Creates, updates, and submits deal registrations for channel partners; resolves customer and product information; and handles product line item management including additions and removals.
        • Security Incident Response AI agents -- The following AI agents are available for Security Incident Response.
          • EDR AI agent -- This Security Incident Response agent retrieves host details or isolates a host associated with a security incident.
          • Exchange online integration handling AI agent -- This Security Incident Response agent searches for and deletes emails related to a security incident.
          • Observable analysis AI agent -- This Security Incident Response agent performs threat lookups, observable enrichment, sighting searches, and block requests against observables in a security incident.
          • Security incident activities handling AI agent -- This Security Incident Response agent manages security incident core activities, ensuring efficient and effective handling of incidents, problems, change requests, and security incident response tasks. It is intended for use by security incident management teams.
          • Security incident resolution AI agent -- This Security Incident Response agent walks the user through resolving a security incident by generating and executing a resolution plan.
          • Security incident retrieval AI agent -- This Security Incident Response agent searches for security incidents using filters and optionally summarizes individual incidents.
          • Security incident shift handover AI agent -- This Security Incident Response agent adds a security incident to a shift handover report, walking the user through each section for review.
          • Security incident wrap up generator AI agent -- This Security Incident Response agent can close a security incident by performing all pre-closure validations. It can also generate close notes, generate post incident analysis, post work note, and update the state of the security incident to close it.
          • Security metrics analysis AI agent -- This Security Incident Response agent calculates and analyzes security incident response metrics for an individual analyst or a team over a specified time range.
        • ServiceNow AI Platform AI agents -- The following AI agents are available for ServiceNow AI Platform.
          • Access Analysis Agent -- The Access Analysis Agent lets you ask whether a user, group, or role can access something on your ServiceNow instance. It uses guided, conversational workflows in the ServiceNow Otto panel.
          • ACL Explainer AI agent -- The agent explains how access control lists (ACLs) are configured. It reads one or more ACLs that govern a table or field for an operation, and describes their roles, conditions, scripts, and admin overrides. The agent is read-only: it doesn't evaluate access, recommend changes, or modify ACLs.
            • Using the ACL explainer AI agent -- The agent explains how access control lists (ACLs) are configured. It reads one or more ACLs that govern a table or field for an operation, and describes their roles, conditions, scripts, and admin overrides. The agent is read-only: it doesn't evaluate access, recommend changes, or modify ACLs.
          • AI Analytics Q and A AI agent -- This AI agent answers natural language questions about AI Analytics. It covers KPI definitions, dashboard widgets, source tables, data flows, deflection log states and scenarios, the deflection and metric frameworks, and ServiceNow platform scripts.
          • AICT security analyzer AI agent -- This AI agent generates context for a detected AI security event by aggregating asset, prompt, cross-threat, and correlation data. It then computes a confidence score from detection strength, event risk, and authorization signals.
          • AICT AI asset description auto-populator AI agent -- This AI agent generates and applies descriptions to AI assets using vendor, model, and manufacturer metadata.
          • AICT deactivate dormant asset AI agent -- This AI agent analyzes and retires dormant AI assets by running comprehensive analysis and creating offboarding change requests.
          • AICT life cycle task reminder AI agent -- This AI agent sends automated email reminders to task owners for overdue and dormant life cycle tasks on high-priority AI assets.
          • AICT outcome ranker AI agent -- This AI agent ranks AI insight outcomes by relevance to each user persona based on their role and responsibilities.
          • Approval assistance AI agent -- This AI agent handles all queries related to approval records for the current user.
          • Decomposition AI agent -- This AI agent takes resolution steps as input, and then analyzes and breaks down each resolution step into a clear, structured set of smaller, actionable substeps. It then creates records based on user preference. This enables precise execution, improves task clarity, and supports automation and auditability of resolution workflows.
          • Domain Separation AI agent -- The Domain Visibility AI agent enables Domain Admins to manage user domain visibility using guided, conversational workflows in the ServiceNow Otto panel.
          • plat-ai-email-action-and-information-ai-agent --
          • plat-ai-email-on-existing-parent-lead-ai-agent --
          • plat-ai-email-to-new-task-creation-ai-agent --
          • Error analysis and remediation AI agent -- This AI agent is helps admins and operators investigate Error Framework error codes, analyze root causes, and execute preconfigured remediation actions.
          • Explain SLA AI agent -- This agent explains Service Level Agreement (SLA) details to the user based on the provided task number. It retrieves the matching SLA using timer configurations, along with SLA breakdown details, task SLA information, and an SLA timeline summary.
          • Image processor AI agent -- This AI agent lets users upload image attachments and create task records by analyzing them. I
          • Issue readiness AI agent -- This AI agent scans the record fields and context of a ticket so it can determine if it is ready for a fulfiller to work on it.
          • Issue trend analysis AI agent -- This AI agent analyzes grouped task data from cases, incidents, problems, or other tables to identify recurring issues and root causes.
          • Model provider configuration AI agent -- This AI Agent helps administrators understand whether their configured third-party LLM providers use OEM (managed by ServiceNow) or bring-your-own-key integration.
          • Next action recommendation AI agent -- This AI agent identifies the optimal steps for resolving tasks by reviewing similar record details, related list record details, relevant knowledge articles, and web search results.
          • Prioritize work AI agent -- This AI agent retrieves user-assigned tasks, scoring them by priority using metadata and Service Level Agreement (SLA) data.
          • Problems investigation AI agent -- This AI agent specializes in root cause identification, impact assessment, and resolution planning. It analyzes problem details, associated incidents, similar incidents, change requests, and affected configuration items to provide a structured and comprehensive analysis.
          • Record field value prediction AI agent -- This AI agent can predict fields for an incoming record.
          • Record management AI agent -- This AI agent can fetch, update, create a record, link a knowledge base (KB) article, and copy an attachment to a record with details provided by the user.
          • Request status AI agent -- This AI agent answers inquiries about existing tickets that were created by or are currently opened by the logged-in user. It should be triggered only when the user explicitly references an existing ticket (for example, by asking for ticket status, updates, comments, or history).
            • Using the request status AI agent -- This AI agent answers inquiries about existing tickets that were created by or are currently opened by the logged-in user. It should be triggered only when the user explicitly references an existing ticket (for example, by asking for ticket status, updates, comments, or history).
          • Search Q&A AI agent -- This agent searches available resources to answer user queries, serving as the fallback agent when other agents cannot handle a request.
          • ServiceNow record navigator AI agent -- This AI agent surfaces ServiceNow records as clickable navigation views. It handles retrieval-style queries ("show me open P1 incidents") and navigation-style commands ("take me to changes assigned to David").
          • Smart documents AI agent -- This Document Management AI agent help users interact with document content by providing summaries, FAQs, and answers to their specific questions. It only works within the ServiceNow Document Viewer.
          • Survey analysis AI agent -- This AI agent extracts and validates date ranges from user input, including natural language expressions. It analyzes survey data (such as questions, responses, and triggered records) to extract key metrics, identify trends, and deliver actionable insights for informed decision-making.
          • Survey filling data collection AI agent -- This AI agent collects data related to the case, incident, or request and the survey questions raised to collect feedback on it.
          • Survey response suggestion AI agent -- This AI agent suggests answers to questions in the survey by using details from case, incident, or request.
          • Troubleshooting AI agent -- This AI agent triages an Automated Test Framework (ATF) test failure.
          • Update work plan AI agent -- This AI agent receives structured plan data from the orchestrator, constructs a valid JSON payload, and updates the finalized work plan in the database.
          • Web automation AI agent -- This AI agent executes automated actions across any web page, enabling form filling, clicking, data extraction, and navigation tasks.
          • Web research and recommendation AI agent -- This AI agent resolves issues by analyzing the problem and generating resolution steps using web search tools.
          • Work allocator AI agent -- This AI agent automatically fetches backlog tickets, evaluates agent workloads and performance metrics, and assigns tickets to agents in a way that optimizes distribution and operational efficiency.
          • Content Understanding AI agents -- The following AI agents are available for Content Understanding.
          • Knowledge Management AI agents -- The following AI agents are available for Knowledge Management.
          • MID Server AI agents -- The following AI agents are available for MID Server.
            • MID common AI agent -- This AI agent helps users and support personnel to identify, analyze, and resolve MID Server issues.
            • MID keystore AI agent -- This AI agent helps IT administrators diagnose and resolve MID Server keystore problems and manage MID Server health.
            • MID network AI agent -- This AI agent helps administrators and support personnel diagnose and resolve MID Server connectivity issues in a ServiceNow instance.
            • MID upgrade AI agent -- This AI agent helps admins diagnose and resolve 'Upgrade Failed' issues on MID Servers by automating the identification, script deployment, error collection, and resolution workflow.
          • Notifications AI agents -- The following AI agents are available for Notifications.
            • Email generator AI agent -- This AI agent composes and sends emails (including new messages or replies) based on the provided context.
            • Intent executor AI agent -- This AI agent executes admin-defined actions, such as workflows or creating reply responses based on matched intent.
            • Intent identification AI agent -- This AI agent analyzes and identifies the input email body intent. A list of admin-configured intents are compared with the input email body for a potential match.
            • Notification AI agent -- This AI agent creates or edits notification records through natural‑language interaction.
            • Notification content AI agent -- This AI agent prepares email notification templates and layouts. It begins by analyzing user input to understand the notification's content requirements and design expectations. Before generating any content, the agent searches for similar existing templates and presents the results to the user.
          • Setup Hub AI agents -- The following AI agents are available for Setup Hub.
            • Group and roles assignment AI agent -- This ServiceNow Otto for Setup AI agent provisions access by creating groups, adding users to a group, assigning roles to a group, and adding users to a role.
            • IA operational data workflow AI agent -- This ServiceNow Otto for Setup AI agent automates the configuration of data imports by handling the creation of data sources, import sets, and transform maps.
            • Implementation plan executor AI agent -- This ServiceNow Otto for Setup AI agent is responsible for executing the implementation plan, carrying out each defined step, and ensuring the plan is completed as designed.
            • Implementation plan generator AI agent -- This ServiceNow Otto for Setup AI agent collects user input by asking configured questions, analyzing the full conversation to derive a precise technical intent, and then generating a step‑by‑step implementation plan.
            • Implementation plan manager AI agent -- The implementation plan manager agent orchestrates an implementation by coordinating the plan generator and plan executor agents. It helps to ensure that your technical intent is converted into a clear plan and executed safely and correctly.
            • Initialize IA orchestrator AI agent -- This ServiceNow Otto for Setup agent automatically triggers the appropriate Virtual Agent topic to streamline setup and onboarding for users on your ServiceNow instance.
            • SLA management AI Agent -- This ServiceNow Otto for Setup agent enables administrators to create and edit SLA definitions through a conversational interface. The agent guides you through SLA configuration, including setting target type (Resolution/Response), duration, table, schedule, start/pause/stop conditions, and flow associations.
            • SSO configuration AI agent -- This ServiceNow Otto for Setup AI agent guides administrators through secure Single Sign-On (SSO) setup for ServiceNow using SAML or OpenID Connect (OIDC). The agent collects and validates identity provider details, creates authentication configurations, and guides users through review, testing, and activation.
            • Update set AI agent -- This ServiceNow Otto for Setup AI agent helps administrators and developers upload, review, and commit XML update sets efficiently.
        • ServiceNow Otto for Creator AI agents -- The following AI agents are available for ServiceNow Otto for Creator.
          • Build Agent -- This AI agent enables developers to create, edit, and deploy full-stack ServiceNow applications to update sets that encompass both user interface and back-end components.
          • Catalog AI agent -- This ServiceNow Otto for Creator agent gathers, validates, and tracks all required inputs for a given Service Catalog item.
          • Module creator AI agent -- This ServiceNow Otto for Creator agent Converts natural language requests into structured JSON definitions for ServiceNow application navigator modules.
          • Playbook activity context AI agent -- This ServiceNow Otto for Creator agent helps users complete ServiceNow forms by fetching form fields, automatically matching pre-filled field values, and prompting for any missing required information. The agent saves the summary of what it has done.
          • Playbook data gathering and processing AI agent -- This ServiceNow Otto for Creator agent is a assistant that consolidates data gathering, processing, and slot-filling capabilities. It handles end-to-end playbook execution using a broad toolkit of retrieval, reasoning, and action-oriented functions. The agent also helps with tasks related to processing of files attached to instance records.
          • Release lifecycle documentation AI agent -- This ServiceNow Otto for Creator agent generates release notes and update set descriptions in natural, human-friendly language for business stakeholders, within a maximum 4000 character limit.
          • Theme Builder AI agent -- This ServiceNow Otto for Creator agent assists in creating and managing themes for user interfaces. It is intended for use by UI/UX designers, developers, and anyone responsible for maintaining the visual consistency of their organization's digital properties.
          • UI builder AI agent -- This agent helps users edit pages and answer questions within the ServiceNow UI Builder editor.
        • ServiceNow Vault AI agents -- The following AI agents are available for ServiceNow Vault.
          • Access Observer configuration manager AI agent -- This ServiceNow Vault agent helps users to manage Access Observer configurations for specific fields
          • Access validation for privacy advanced configurations AI agent -- This ServiceNow Vault agent checks a user's access to manage privacy policy advanced configuration.
          • Create Data Privacy advanced configuration AI agent -- This ServiceNow Vault agent helps users fetch, create, activate, and link data privacy policy configurations across data channels.
          • Custom app recommendations AI agent -- This ServiceNow Vault agent lists the custom apps on the instance, and shows recommendations along with the available protections for the selected apps.
          • Data Discovery policy and job manager AI agent -- This ServiceNow Vault agent checks whether a given list of tables supports data discovery scanning. The agent then creates data discovery job policies using these tables, and creates discovery job policies and schedules and data discovery jobs using the created policy.
          • Data Discovery recommendation AI agent -- This ServiceNow Vault agent provides job info, findings, attributes, and related details for a list of tables provided. The agent also returns scan recommendations you can use to create policy and schedule the discovery job by another agent.
          • Data Discovery util AI agent -- This ServiceNow Vault agent assists data stewards in scheduling and managing data discovery jobs by verifying required roles, entitlements, and subscriptions. The agent categorizes discovered data patterns into compliance groups to support regulatory and security requirements. It also help user to add tags to data patterns on demand.
          • Data Discovery workflow lookup AI agent -- This ServiceNow Vault agent receives provide recommendation for different tables associated with workflows, and identifies what kind of sensitive data can present in those tables such as PII,PFI,PCI,PHI,FCI.
          • Data pattern list AI agent -- This ServiceNow Vault agent helps users associate data patterns to an data privacy policy configuration. It retrieves the list of available data patterns, captures the user’s selections, extracts the related sys_ids, assigns data patterns to data privacy policy configuration and validates it.
          • DP record selector agent AI agent -- This ServiceNow Vault agent fetches data using tools or topics to display list of choices related to the action.
          • Edit Data Privacy advanced configuration mapping AI agent -- This ServiceNow Vault agent helps users complete tasks related to edit data privacy advanced configuration mapping agent.
          • Edit privacy advanced configuration AI agent -- This ServiceNow Vault agent helps users complete tasks related to edit privacy advanced configuration agent.
          • Summarize Access Observer logs AI agent -- This ServiceNow Vault agent summarizes access observer logs and provides detailed breakdowns by caller type, users, and roles for specific table and column combinations.
          • Vault crypto module manager AI agent -- This ServiceNow Vault agent manages the Vault crypto module configuration and access policies. The agent handles encrypted field configurations for fields, and manages module access policies for roles.
          • Anonymization Policy Creation AI agent -- The agent guides Data Privacy administrators through creating an anonymization policy. It captures the data channel, policy name, and data class, creates a draft policy, recommends anonymization techniques by data type, and then tries to publish the policy, explaining anything that must be fixed first.
          • Real Time Anonymization(RTA) Policy Configuration AI agent -- The agent creates Real-Time Anonymization (RTA) policies that mask or anonymize sensitive column values as they're accessed. It guides the user through naming the policy, selecting the target columns to anonymize, and choosing any child tables that should inherit the same protection.
          • Field Access Auditor AI agent -- The agent retrieves the non-elevated user roles that have access to a table field, lets the user add or remove roles, and returns the finalized list of roles.
          • Anonymization Job Scheduler AI agent -- The agent helps Data Privacy administrators schedule anonymization jobs against existing records by using a published anonymization policy. It checks for conflicting jobs, configures the job frequency, targets, and conditions, offers an optional dry run, and asks for explicit confirmation because starting a job is irreversible.
          • Real Time Anonymization(RTA) Validation AI agent -- The agent confirms that Real-Time Anonymization (RTA) policy creation is supported for the user, and helps the user configure the tables and active data patterns that an RTA policy requires. The agent can add tables and add or remove active data patterns.
          • Real Time Anonymization(RTA) Test AI agent -- The agent tests Real-Time Anonymization (RTA) by taking a text string from the user and returning the anonymized version.
        • Software Asset Management AI agents -- The following AI agents are available for Software Asset Management.
        • Sourcing and Procurement Operations AI agents -- The following AI agents are available for Sourcing and Procurement Operations.
          • Procurement inquiry analysis AI agent -- This Sourcing and Procurement Operations agent is an educational assistant for procurement and sourcing terminology questions. The agent scans policy manuals and help articles to deliver plain-language explanations of purchase orders, requisitions, sourcing requests, and procurement cases. It can connect users to a live agent if knowledge articles don't have sufficient information.
          • Procurement product recommendation AI agent -- This Sourcing and Procurement Operations agent can browse the catalog and create orders. The agent matches user requirements against available items, then routes to submission forms based on vendor status and dollar thresholds. Accepts and processes uploaded quote documents or SOW (Statement of Work) files to extract line items and pricing.
          • Procurement request tracking AI agent -- This Sourcing and Procurement Operations agent provides a summary of a procurement request. It can provide current status and next steps for the request.
          • Spend categorization AI agent -- This Sourcing and Procurement Operations agent predicts and populates product and spend categories in purchase requisition lines, reducing manual effort and improving data accuracy.
          • Contract Optimization Opportunity Finder agent -- This Sourcing and Procurement Operations agent analyzes supplier contracts to identify and create savings opportunities by analyzing price escalations, renewal caps, and payment terms. It can also answer follow-up questions about spend data, contracts, savings opportunities, pipeline projects, and savings calculations.
          • Spend Optimization Opportunity Finder agent -- This Sourcing and Procurement Operations agent compares on-contract and off-contract purchase order pricing to identify savings opportunities, quantifying the potential savings from redirecting off-contract spend to existing supplier contracts. It can also answer follow-up questions about spend data, contracts, savings opportunities, pipeline projects, and savings calculations.
          • Supplier Optimization Opportunity Finder agent -- This Sourcing and Procurement Operations agent analyzes spend data to identify supplier optimization opportunities across non-preferred supplier spend, unconsolidated spend, spend fragmentation, and supplier performance and risk. It can also answer follow-up questions about spend data, contracts, savings opportunities, pipeline projects, and savings calculations.
        • Strategic Portfolio Management AI agents -- The following AI agents are available for Strategic Portfolio Management.
          • Project eligibility analysis AI agent -- This Strategic Portfolio Management agent performs checks for project and project task related requests. The agent analyzes requests to check impact on a project due to project task. It checks if the project summary email skill is enabled for the instance and whether the skill was enabled for a given project.
          • Project summarization AI agent -- This Strategic Portfolio Management agent assists project managers to get a summary of the project. The agent helps in keeping their projects on track, by providing actionable and proactive updates on critical changes to projects. It also generates the project summaries.
          • Validate the work item and generate stories AI agent -- This Strategic Portfolio Management agent transforms Enterprise Agile Planning work items (epics and features) into a set of well-formed, actionable user stories. It evaluates work items to verify that it contains sufficient information, and guides users through a structured validation process.
        • Supplier Lifecycle Operations AI agents -- The following AI agents are available for Supplier Lifecycle Operations.
          • Supplier data steward AI agent -- This Supplier Lifecycle Operations agent manages supplier onboarding by verifying details, detecting duplicates, presenting scorecards for review, creating records, and updating case status.
          • Supplier data validator AI agent -- This Supplier Lifecycle Operations agent takes a supplier case number and initiates the supplier banking task validation process. The validation process compares the bank account proof against the banking details provided by the supplier contact.
          • Supplier document strategy generator agent -- This Supplier Lifecycle Operations agent assists with supplier onboarding by retrieving the supplier's region and industry, then identifying customized onboarding tasks that meet compliance and regulatory requirements.
          • Supplier approval AI agent -- This Supplier Lifecycle Operations agent performs the supplier activation or supplier rejection tasks during supplier approval process.
        • Telecommunications, Media and Technology AI agents -- The following AI agents are available for Telecommunications, Media and Technology.
          • Customer Success Management AI agents -- The following agents are available for Customer Success Management.
            • AI insight AI agent -- The agent answers questions about a customer engagement or account. It reports health scores, adoption scores, value realization, risks, contract value, and other engagement data, and it forecasts scores and recommends improvements.
            • Draft meeting scheduler AI agent -- The agent edits a draft touchpoint meeting for a customer success agent. It updates the invitees, subject, agenda, date and time, duration, and meeting link, then sends the invitation.
            • Email communication manager AI agent -- The agent retrieves the latest released product information, creates draft emails, refines them from user input, and sends them to specific recipients.
            • Product adoption roadmap AI agent -- The agent creates a product adoption roadmap for a customer. It analyzes the engagement and similar engagements, creates the roadmap, and arranges lanes and items to match the customer's goals.
            • Renewal analysis AI agent -- The agent analyzes a renewal for a contract or engagement. It combines insight scores and value realization data into a renewal report and offers to create a renewal success play.
            • Success health monitor AI agent -- The agent retrieves metric trend analysis for engagements. It creates a risk signal or risk occurrence for each engagement whose health metrics are declining.
            • Success insights AI agent -- The agent populates score data from a selected data source and provides trend analysis of the scores to the customer success agent.
            • Success risk solution AI agent -- The agent resolves unaddressed risk signals. It identifies success plays based on machine learning similarity, AI Search, or a decision table, and starts the solution flows for the selected risk.
            • User resource recommender AI agent -- The agent filters and ranks users by relevance and adds the top-ranked users to the input record. It runs without user interaction by using the context that starts it.
            • Value realization assessor AI agent -- The agent identifies the value realized for an engagement and returns the value data to the customer success agent.
          • Customer Service Problem Management AI agents -- The following agents are available for Customer Service Problem Management.
            • Billing account information collector AI agent -- The agent retrieves the details of a billing inquiry case and uses the account number on the case to look up the matching billing account. It returns the billing account number, master plan instance number, and master plan instance description. Other AI agents use this agent to obtain billing account information.
            • Billing invoice data collector AI agent -- The agent retrieves the latest and previous invoices for a billing account, collects the line items on the latest invoice, and validates the pending amount. It compares the two invoice amounts and, when the latest invoice is higher, identifies the line item and the sold product behind the increase.
            • Customer interaction context gatherer AI agent -- The agent retrieves the details of a customer interaction and identifies the sold product that the interaction refers to. It gives customer service representatives the account, contact, category, status, and sold product context that they need when they troubleshoot voice quality issues.
            • Customer payment status AI Agent V2 -- The agent checks whether a customer has outstanding payments on their account. It runs without user interaction, collecting the payment status in the background and passing the result to the orchestrator. It does not troubleshoot payments or call other agents.
            • Network correlation monitor AI agent -- The agent identifies the network services, customer accounts, and products that a network incident affects. It checks for service problem cases created recently and, with the user's approval, creates a major service problem case, links the incident and related cases to it, and creates child cases for the affected accounts.
            • Network remediation generation AI agent -- The agent reads the resolution steps from the work notes of a network incident and maps each step to a task type: incident task, work order, or change request. It then creates the mapped tasks and displays a link to each one.
            • Network ticket actionable steps generation AI agent -- The agent generates actionable resolution steps for a network incident from similar past incidents, and falls back to generic steps when no similar incidents exist. The user can change the steps before the agent adds them to the work notes of the incident.
            • Network ticket resolution AI agent -- The agent collects the details of a network incident, analyzes the associated alert to produce a summary, and finds knowledge articles relevant to the incident. The user chooses whether to add the alert summary and the articles to the work notes of the incident.
            • On demand service tester AI Agent V2 -- The agent analyzes a task by running the test groups that apply to it. It creates a diagnostic task, runs the test groups, and collects the final test run result. It returns the diagnostic task and the result to the orchestrator without displaying them to the user.
            • Preliminary troubleshooter AI Agent V2 -- The agent triages a task by retrieving relevant knowledge articles and similar historical tasks, and consolidates them into a resolution plan with recommended next steps. It writes the plan, along with any customer payment information, to the work notes of the task.
            • Service repair AI agent V2 -- The agent reviews the results of a service test and creates a repair task when the test fails. It summarizes the diagnostic task, the overall test result, and any repair tasks created, and writes that summary to the work notes of the task.
            • Task information collector AI Agent V2 -- The agent gathers the details of a task and verifies that the task qualifies for further troubleshooting. It runs without user interaction, and returns the task details, the verification status, and the verification response to the orchestrator.
            • Telecom customer support AI voice agent -- The AI voice agent helps a consumer troubleshoot a broadband service issue over the phone. It validates the caller, finds their active services, and walks them through the troubleshooting steps from a knowledge article one step at a time. It can also check the contract termination status.
            • Ticket creation AI agent -- The agent creates a service problem case for a connectivity issue. It checks that the sold product, short description, and experience profile are available, creates the case, and displays the case number with a link to the new record.
            • Ticket readiness AI agent -- The agent predicts the category, subcategory, assignment group, short description, and description for a network incident from similar historical incidents. It also estimates the resolution duration and retrieves the SLA duration, then updates the incident or its work notes with the recommendations the user accepts.
          • Service Exchange AI agents -- The following AI agents are available for Service Exchange.
            • Registration error monitor AI agent -- This AI agent checks a registration number and connection against the Service Exchange error table, and then provides a detailed summary of any reported Service Exchange errors. This summary helps users or other AI agents make informed decisions and take appropriate action to resolve registration issues.
            • Registration initiator AI agent -- This AI agent initiates the registration process and manages its early stages, including creating the registration record.
            • Registration monitor AI agent -- This AI agent monitors registration task state changes, validates system configurations, and posts audit results to work notes.
          • Telecommunications Customer 360 AI agents -- The following agents are available for Telecommunications Customer 360.
            • Telecom Smart Actions Agent AI agent -- The agent gathers telecom customer context from an account or consumer record and runs a pre-diagnostic sweep across product inventory and five service health checks: duplicate cases, open incidents, work orders, alerts, and outstanding billing. It then produces a support summary and answers follow-up questions.
          • Telecommunications Network Inventory AI agents -- The following AI agents are available for Telecommunications Network Inventory.
            • Rack placement AI agent -- This AI agent finds a data center rack allocation that fits the capacity requirements of a change request. It validates the request, applies the placement policies for the data center, and records the outcome on the change request.
        • Unified Security Exposure Management AI agents -- The following AI agents are available for Unified Security Exposure Management.
          • VR data retrieval agent AI agent -- This Unified Security Exposure Management agent answers questions about vulnerability response data by constructing and executing table queries.
          • Remediation compliance analysis AI agent -- This Unified Security Exposure Management agent provides insights around remediation target compliance. It provides SLA or compliance statistics about remediation targets. The agent can break down these numbers by attributes such as severity, assignment group, or configuration class item class.
          • Vulnerability exposure analysis AI agent -- This Unified Security Exposure Management agent assesses vulnerability on business services or configuration items.
        • Workflow Data Fabric AI agents -- The following AI agents are available for Workflow Data Fabric.
          • Automation finder AI agent -- This Workflow Data Fabric agent fetches automation records from tables on your instance. The agent discovers relevant automations for a specified asset, estimates cost and time savings, saves the discovered automations, and presents a value insights summary to the user.
          • Automation table discovery AI agent -- This Workflow Data Fabric agent collects asset, time, and scope inputs from the user and returns a structured JSON payload identifying the target execution tables for automation discovery.
          • Workflow data fabric flow generation AI agent -- This Workflow Data Fabric agent transforms a user's natural-language integration intent into a generated Workflow Studio flow.
          • Workflow data fabric product knowledge AI agent -- This Workflow Data Fabric agent retrieves and summarizes knowledge articles. The agent passes the user's query verbatim to the search tool, extracts factual content from matching articles, and produces a consolidated summary with references to source documents.
          • Workflow data fabric product recommendation AI agent -- This Workflow Data Fabric agent evaluates integration requirements, data movement needs, communication flows, and automation objectives expressed in the user's prompt and determines the most suitable workflow data fabric product.
          • Workflow data fabric spoke asset discovery AI Agent -- This Workflow Data Fabric agent finds specific flows, subflows, and actions inside a named spoke that fulfill a user's stated automation goal. This agent is triggered only when a user has identified a spoke and wants to explore what reusable assets it contains for their use case.
          • Workflow data fabric spoke install advisor AI Agent -- This Workflow Data Fabric agent helps you search for available IntegrationHub spokes that aren't installed on the instance. This agent takes the your search query, retrieves matching non-installed spokes from the instance catalog, and returns a prioritized list of candidates with installation links.
        • Zero Copy Connector for ERP AI agents -- The following AI agents are available for Zero Copy Connector for ERP.
          • ERP action invoker AI agent -- This AI agent gathers user inputs for a specific operation in Zero Copy Connector for ERP.
          • ERP data fetcher AI agent -- This Zero Copy Connector for ERP AI agent retrieves information about relevant models and model operations. The AI agent currently supports Read operations.
          • ERP output formatter AI agent -- The Zero Copy Connector for ERP AI agent formats and refines the output from the ERP action invoker AI agent.
          • OData service recommender AI agent -- The OData service recommender AI agent identifies relevant OData services and endpoints. The AI agent can create a model for the identified service if a model does not already exist.
      • About AI agents and agentic workflows -- AI agents and agentic workflows pursue a goal across multiple steps, planning and acting with limited human intervention to resolve an issue or complete a request. Where a generative AI skill completes one task on demand, an agentic workflow coordinates one or more agents to carry a process from start to finish.
      • AI Agent Studio -- Build and deploy autonomous AI agents that automate complex workflows. AI Agent Studio is your command center for creating, configuring, and deploying autonomous AI agents that learn your business processes and act on them. Configure agents that learn your processes and handle routine work at scale—while you stay in control and focus on strategic priorities.
        • Explore AI Agent Studio -- Create, manage, and test AI agents and agentic workflows in one centralized space to build self-executing solutions that help you achieve your business goals.
        • Configure AI Agent Studio -- Configure AI agents, agentic workflows, and tools so that AI agents can plan and execute tasks using your record data and knowledge base content.
          • Install AI Agent Studio -- Install Now Assist AI agents on your ServiceNow instance to enable the agentic AI experience.
          • Set up AI Agent Studio -- The default (base system) AI agents provide preconfigured agentic workflows that address common business challenges across ServiceNow applications. Before activating the default AI agents, you must verify that your instance meets the prerequisites and complete the required configuration steps.
          • AI Agent Studio settings -- Configure general settings for AI Agent Studio and agentic AI assets.
            • Enable AI Guardian for AI agents -- Identify and block offensive messages that are sent by human agents automatically by enabling AI Guardian in AI agents. With this capability, you can help reduce your agentic workflow or test from being exposed to harmful content.
            • Set up long-term memory -- Make AI agents remember your preference or facts from previous interactions and use memories for more focused conversations.
              • Long-term memory categories for Now Assist AI Agents -- Long-term memory (LTM) categories define the types of semantic information that a Now Assist AI agent can learn and retain about users over time. You can add new categories and map them to specific agents to personalize agent responses based on accumulated user context.
              • Create long-term memory category -- Create a category that defines the type of user information an AI agent can remember, such as work context or user preferences.
              • Map a long-term memory category to an AI agent -- Map the created long-term memory category to the agents that should use it. Categories must be mapped individually to each agent; they are not applied globally by default.
            • Select the model provider -- Choose the large language model (LLM) service provider for Now Assist AI agents in AI Agent Studio.
          • Multiple conversations -- Multiple active conversations enable live agents to maintain separate conversations for different records. You can preserve the context of multiple conversations and enable multiple AI agents to interact at the same time through the Now Assist panel.
          • Citations in Now Assist AI agents -- Citations appear on the ServiceNow Otto panel when AI agents and agentic workflows provide summaries for similar incidents and knowledge articles.
            • Hide citations -- Disable citations for specific agentic workflows or AI agents in AI Agent Studio where citations aren’t required or involve confidential information.
          • Follow-up conversations -- AI agents continue with follow-up conversations after the AI agent execution is complete.
          • Usage, failure, and latency notifications -- Add or change recipients to email notifications triggered by unexpected or undesired behavior in AI agent and agentic workflow executions.
          • Implement access control in AI Agent Studio -- Implement security in AI Agent Studio through access control lists (ACLs), user identities, and role filtering with the access control-based security measures in the agentic system.
        • Create an AI agent -- Create an AI agent in AI Agent Studio to solve problems for your users and coordinate with other AI agents in agentic workflows.
          • Create an AI agent from an automation opportunity -- Use automation opportunities identified on your instance to create AI agents in AI Agent Studio.
          • Define expected behavior -- In the guided setup for an AI agent, write a clear description defining your AI agent, its role, and the instructions it should perform to accomplish tasks.
          • Add tools and information -- Add a tool to an AI agent to enable different functionalities and help your AI agents achieve their objectives.
            • AI skill -- Add a generative AI skill to an AI agent to expand its capabilities with reusable operations and custom functionality.
            • Catalog item -- Add a catalog item to an AI agent in AI Agent Studio so that your users can access conversational catalog items.
            • Conversational topic -- Add a Virtual Agent topic to an AI agent in AI Agent Studio so that you can use conversations to get additional information from the user. For example, a conversational topic could be used to let a user select a date range for surveys.
            • Deep research -- Add a deep research tool to an AI agent so it can search multiple sources and provide answers with sources listed.
            • Desktop action -- Add a desktop action as a tool to an AI agent so that AI agents can automate tasks in desktop and web-based applications.
            • File upload -- Upload files for analysis by an AI agent in AI Agent Studio to grant your AI agent access to specialized knowledge.
            • Flow action -- Add a flow action to an AI agent in AI Agent Studio so the agent can run it as a reusable operation that automates ServiceNow AI Platform features, without writing code.
            • Knowledge graph -- Add a Knowledge Graph to an AI agent in AI Agent Studio that uses the structured and unstructured data from different ServiceNow records to enhance the performance of AI agents.
            • Record operation -- Add a record operation tool to an AI agent to enable it to perform record operations on tables in your instance.
            • Script -- Add a script tool to an AI agent to enable it to execute custom scripts to perform specialized tasks.
            • Search retrieval -- Add a search retrieval tool to an AI agent to enable it to retrieve and incorporate relevant information from defined sources.
            • Subflow -- Add a subflow tool to an AI agent in AI Agent Studio. Subflows are reusable sequences of processing steps that can be called from within a flow.
            • Web search -- Add a web search tool to an AI agent to enable it to search the web and retrieve relevant information.
          • Define access -- Define security controls for an AI agent to determine which users can access it and what permissions they have.
          • Add a trigger -- In the guided setup for an AI agent, add triggers to run the AI agent automatically when certain conditions are met.
          • Select channels and messages -- In the guided setup for an AI agent, select whether to use it in the ServiceNow Otto panel or an Otto assistant.
          • Modify an AI agent -- Modify an AI agent in AI Agent Studio to refine its performance, align with business goals, or enable it to perform new tasks.
        • Integrate external AI agents -- Integrate external AI agents in AI Agent Studio to connect the ServiceNow AI Platform with third-party agentic AI providers as primary agents.
          • Agent2Agent Protocol -- Agent2Agent (A2A) is an open standard that enables cross-platform AI agent communication by associating each agent with an Agent Card containing provider information.
          • Create an external AI agent -- Create external AI agents in AI Agent Studio to connect the ServiceNow AI Platform with third-party agentic AI providers.
          • ServiceNow AI agents as secondary agents -- Secondary agents are specialized AI agents that handle specific workflow tasks delegated by a primary agent or user. You can connect your ServiceNow agent to other agentic AI model providers using the Agent2Agent protocol.
          • Set up A2A authentication -- Configure ServiceNow AI agents as secondary agents over the Agent2Agent (A2A) protocol by setting up authentication and enabling external agent interoperability.
          • A2A API Key credential behavior -- Starting in Now Assist AI Agents 7.1.x, the API Key credential record determines the header in each A2A request. The flow action no longer adds the header automatically.
          • Modify an external AI agent -- Modify an external AI agent in AI Agent Studio to refine its performance, align with business goals, or enable it to perform new tasks.
        • Create an agentic workflow -- Create an agentic workflow in AI Agent Studio to coordinate multiple AI agents and solve complex problems that require collaboration across specialized agents.
          • Define expected behavior -- In the guided setup for an agentic workflow, write a clear description defining your agentic workflow and the instructions it should perform to orchestrate AI agents and accomplish complex tasks.
          • Add AI agents -- Add AI agents to an agentic workflow so they can work together to accomplish complex tasks.
          • Define access -- Define security controls for an agentic workflow to determine which users can access it and what permissions they have.
          • Add a trigger -- In the guided setup for an agentic workflow, add triggers to run the agentic workflow automatically when certain conditions are met.
          • Select channels -- In the guided setup for an agentic workflow, configure where users can engage with the agentic workflow.
          • Modify an agentic workflow -- Modify an agentic workflow in AI Agent Studio to refine its performance, align with business goals, or enable it to perform new tasks.
        • Manually test an agentic AI asset -- Manually test an AI agent or agentic workflow to verify it functions as defined and achieves the desired objectives.
        • Create test scenarios -- Create different scenarios to evaluate your agentic AI asset's performance across multiple executions.
        • Evaluate an agentic AI asset -- Evaluate your agentic AI asset's performance against defined scenarios to identify issues and opportunities for improvement.
        • Duplicate an agentic AI asset -- Duplicate an agentic AI asset to create an identical copy that you can fine-tune with distinct instructions and tools.
        • Deactivate an agentic AI asset -- Deactivate an AI agent or agentic workflow to stop it from running.
        • Reference -- Find more information about user roles, tables, and the different properties that are installed in ServiceNow Otto AI agents.
          • Domain Visibility AI agent -- The Domain Visibility AI agent enables Domain Admins to manage user domain visibility using guided, conversational workflows in the ServiceNow Otto panel.
          • Troubleshoot manual testing -- When testing an agentic AI asset in AI Agent Studio, there are a few common errors that can be addressed before you test again.
          • Troubleshoot AI agents -- Use this troubleshooting guide to resolve issues with AI agents' roles, testing procedures, silent failure diagnosis and reference resources.
          • Troubleshoot external AI agents -- Use this troubleshooting guide to resolve issues with External AI agents' roles, testing procedures, failure diagnosis and reference resources.
        • MCP Client -- The ServiceNow Model Context Protocol Client (MCP Client) allows you to access the Model Context Protocol tools hosted externally and published via an MCP Server in the ServiceNow AI Agent Studio.
          • Explore MCP Client -- The Model Context Protocol (MCP) is a standardized client-server protocol that enables AI applications to discover and interact seamlessly with external tools, data sources, and services. MCP facilitates communication between an AI host application (like AI Agent Studio), an MCP Client embedded in the host, and one or more MCP Servers that expose specific capabilities such as tools.
          • Configuring Model Context Protocol Client -- Configure the MCP Client to execute agentic workflows with AI agents and mapped tools.
          • Adding an MCP Server Console in AI Agent Studio -- An MCP Server Console hosts the APIs and tools required by an AI application. It receives and processes calls from MCP Clients to govern ingress traffic and promote secure access to tools. Adding an MCP Server Console in the AI Agent Studio helps you to leverage the Model Context Protocol as a tool in the ServiceNow agentic AI system.
          • Add Model Context Protocol tool -- Add an MCP tool to an AI agent in the AI Agent Studio so that your users can access the MCP server.
          • Model Context Protocol Client reference -- Find more information about user roles, tables, and the different properties that are installed with the Model Context Protocol Client application.
      • AI Agent Studio (legacy) -- The ServiceNow AI agents are entities that mimic human-like intelligence by using large language models (LLMs). AI agents can perform tasks that range from simple automated responses to complex problem solving. By using AI agents, you can reduce the workloads of your live agents and help increase their productivity.
        • Explore -- Learn how the AI agents enhance live agent productivity by mimicking human-like intelligence to manage tasks ranging from automated responses to complex problem solving.
          • AI Agent Studio overview -- Create, manage, or test AI agents and agentic workflows so that you can create self-executing workflows to help you achieve your business goals.
          • Understand AI agents -- The AI Agent Studio is designed to securely use your data, workflows, and integrations directly within the ServiceNow AI Platform. AI agents can dynamically adjust their actions based on the progress and changing conditions of incidents or cases to help verify that they stay focused on achieving their objectives.
          • AI agents best practices -- AI agents can dynamically adjust the actions that are based on the progress and changing conditions of incidents or cases to help ensure that they stay focused on achieving their objectives.
            • AI agents capabilities -- Lists the features supported by AI agents, including configuration options and functional capabilities.
            • Writing prompts for agentic AI -- By following some general guidelines for creating AI agents and agentic workflows, you can create clear and effective instructions that help maximize their efficiency and effectiveness.
              • Example AI agent -- Use the example AI agent with clear name, description, AI agent role, and list of steps fields to use as a guide when creating your own AI agents.
              • Example agentic workflow -- Use the example agentic workflow with clear name, description, and list of steps fields to use as a guide when creating your own agentic workflows.
          • Group Action Framework -- Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs.
          • Version control -- Version control enables you to track changes made to instructions sent to the LLM for AI agents and agentic workflows.
          • Implement access control in AI agents -- Implement security in AI Agent Studio through access control lists (ACLs), user identities, and role filtering with the access control-based security measures in the agentic system.
          • AI agent learning -- Enhance AI agent learning through episodic memory, enabling agents to improve by learning from past successful interactions.
        • Configure -- Configure AI agents to execute agentic workflows with AI agents and mapped tools.
          • Install ServiceNow Otto AI Agents -- Install ServiceNow Otto AI Agents on your ServiceNow instance to enable the agentic AI experience.
          • Set up AI agents -- The default (base system) AI agents provide preconfigured agentic workflows that address common business challenges across ServiceNow applications. Before activating the default AI agents, you must verify that your instance meets the prerequisites and complete the required configuration steps.
          • Enable AI Guardian -- Identify and block offensive messages that are sent by human agents automatically by enabling AI Guardian in AI agents. With this capability, you can help reduce your agentic workflow or test from being exposed to harmful content.
          • Select the model provider -- Choose the large language model (LLM) service provider for AI agents in AI Agent Studio.
          • Set up long-term memory -- Make AI agents remember your preference or facts from previous interactions and use memories for more focused conversations.
          • GAF -- Set up Group Action Framework (GAF) to improve the response quality, recall speed, and consistency of AI agents.
            • Set up AI Search for GAF -- Configure AI Search to enable Group Action Framework (GAF) to improve quality and consistency of agentic AI and generative AI on the ServiceNow AI Platform.
          • Multiple conversations -- Multiple active conversations enable live agents to maintain separate conversations for different records. You can preserve the context of multiple conversations and enable multiple AI agents to interact at the same time through the ServiceNow Otto panel.
          • Citations in AI agents -- You can see citations on the ServiceNow Otto panel when you execute AI agents and agentic workflows in AI agents that provide summaries to get similar incidents and relevant knowledge articles.
            • Hide citations -- Disable citations for specific agentic workflows or AI agents in AI Agent Studio where citations aren’t required or involve confidential information.
          • Follow-up conversations -- AI agents continue with follow-up conversations after the AI agent execution is complete.
          • Usage, failure, and latency notifications -- Add or change recipients to email notifications triggered by unexpected or undesired behavior in AI agent and agentic workflow executions.
          • Role masking -- Role masking for AI agents and agentic workflows helps users enhance security by enabling them to limit their roles during tool execution and verify that AI agents run with least-access privileges.
        • Create an AI agent -- Create an AI agent in AI Agent Studio to solve problems for your users and coordinate with other AI agents while executing the agentic workflows.
          • Find AI agents -- Find available AI agents in AI Agent Studio to explore your options when creating agentic workflows.
          • Define the specialty -- In the guided setup for an AI agent, write a clear description defining your agent and its role. You can also configure supported LLMs, enable third-party access, and manage long-term memory.
          • Add tools and information -- Add a tool to an AI agent to enable different functionalities and help your AI agents achieve their objectives.
            • Catalog item -- Add a Service Catalog to an AI agent in AI Agent Studio so that your users can access conversational catalog items.
            • Conversational topic -- Add a Virtual Agent topic to an AI agent in AI Agent Studio so that you can use conversations to get additional information from the user. For example, a conversational topic could be used to let a user select a date range for surveys.
            • Defined desktop action -- Add a desktop action as a tool to an AI agent in AI Agent Studio so that AI agents can execute defined path desktop actions for repetitive tasks in desktop and web environment.
            • File upload -- Upload files for analysis by an AI agent in AI Agent Studio to grant your AI agent access to specialized knowledge.
            • Flow action -- Add a flow action to an AI agent in AI Agent Studio. Define the flow action to use it as a reusable operation in automating the ServiceNow AI Platform features without having to write code.
            • Knowledge Graph -- Add a Knowledge Graph to an AI agent in AI Agent Studio that uses the structured and unstructured data from different ServiceNow records to enhance the performance of AI agents.
            • AI skill -- Add a generative AI skill to an AI agent in AI Agent Studio. You can customize the skills to meet the needs of your users in different workflows.
            • Record operation -- Add a record operation to an AI agent in AI Agent Studio to create, update, look up, or delete records.
            • Script -- Create a script to add it to an AI agent in AI Agent Studio. With scripts, you can use the scriptable APIs and back-end integration to support the AI agent.
            • Search retrieval -- Add a search retrieval to an AI agent in AI Agent Studio. Leveraging the Retrieval-Augmented Generation (RAG) enables an AI agent to retrieve and incorporate relevant information from an external source.
            • Subflow -- Add a subflow tool to an AI agent in AI Agent Studio. Subflows are reusable sequences of processing steps that can be called from within a flow.
            • Web search -- Add a web search to an AI agent in AI Agent Studio using a third-party search API such as Microsoft Bing or Google.
          • Define security controls -- In the guided setup for an AI agent, define security controls for who can access the AI agent and what data the AI agent has access to.
          • Add a trigger -- In the guided setup for an AI agent, add triggers to run the AI agent automatically when certain conditions are met.
          • Select channels and status -- In the guided setup for an AI agent, activate the AI agent to use in an assistant in ServiceNow Otto for Virtual Agent, and set the processing messages.
          • Duplicate an AI agent -- Duplicate an existing AI agent in AI Agent Studio so that you can save time by not having to manually configure or create AI agents.
          • Modify an AI agent -- Modify an AI agent in AI Agent Studio to suit your changing business needs.
          • Test execution manually -- Analyze the execution of an AI agent so you can see that it functions the way that you defined it.
          • Test user access -- Run a manual test to verify that only the users you want to access the AI agent can do so.
          • Delete an AI agent -- Delete an AI agent from AI Agent Studio if you no longer need it.
          • Create an external agent -- Create external AI agents in AI Agent Studio to connect the ServiceNow AI Platform with third-party agentic AI providers as primary agents.
            • Integrating external AI agents -- Integrate and configure external agents with the ServiceNow agentic AI system using Agent2Agent (A2A) protocol integration to use in agentic workflows created in the AI Agent Studio.
            • ServiceNow AI agents as secondary agents -- Integrate ServiceNow AI agents into other agentic AI systems, such as Google Cloud or Azure OpenAI.
            • External agents with Agent2Agent -- Create external AI agents in AI Agent Studio to connect the ServiceNow AI Platform with third-party agentic AI providers.
        • Create an agentic workflow -- Create an agentic workflow in AI Agent Studio so that AI agents can coordinate to solve complex problems.
          • Define key requirements -- In the guided setup for an agentic workflow, write a clear description of what the agentic workflow is, add AI agents, and select unsupported AI model providers.
          • Define security controls -- In the guided setup for an agentic workflow, define security controls for who can access the agentic workflow and what data the agentic workflow has access to.
          • Add a trigger -- In the guided setup for an agentic workflow, add triggers to run the agentic workflow automatically when certain conditions are met.
          • Select channels and access -- In the guided setup for an agentic workflow, activate the agentic workflow to use in the ServiceNow Otto panel or UI actions in the Core UI and workspaces.
          • Duplicate an agentic workflow -- Duplicate an existing agentic workflow in AI Agent Studio to save time by not having to manually configure or create agentic workflows.
          • Activate an agentic workflow template -- Activate an agentic workflow that come installed with ServiceNow applications in AI Agent Studio.
          • Modify an agentic workflow -- Make changes to existing agentic workflows in AI Agent Studio to adjust them to suit your business needs.
          • Test execution manually -- Test your agentic workflow in AI Agent Studio to analyze how it functions while it executes the instructions that you defined.
          • Test user access -- Run a manual test to verify that only the users you want to access the agentic workflow can do so.
          • Delete an agentic workflow -- Delete an agentic workflow from AI Agent Studio.
        • Deploy AI voice agents -- AI voice agents are generative AI-powered agents that bring natural, conversational experiences to phone-based support. As part of the broader AI agent ecosystem, they connect with telephony providers to replace rigid menu trees with seamless and human-like interactions that can help make support faster and more intuitive.
        • Execute a run -- Evaluate agentic AI assets against datasets to monitor performance and compare benchmarks.
          • Create a custom metric -- Create a custom metric for evaluating AI agents and agentic workflows to test the outputs against expected responses.
          • Parser tool -- Use the outputs of the agentic evaluation parser tool in your scripts for custom metrics to customize the criteria for effective AI agents and agentic workflows.
          • Guidelines for evaluations -- Learn about agentic evaluation runs and different recommendations for evaluating your agentic AI assets against datasets to check for completion, performance, and tool execution.
        • Examples of using AI agents -- Review different ways that you can leverage the Now Assist AI agents application in agentic workflows across the platform.
          • Resolve an incident -- Help your live agents resolve an incident faster with Now Assist AI agents by using the Now Assist panel.
          • Review and update tickets -- Review the status of your tickets and take standard ticket actions, such as adding comments, using the Ticket Status AI agent in Now Assist in Virtual Agent.
        • Reference -- Find more information about user roles, tables, and the different properties that are installed in ServiceNow Otto AI agents.
          • Domain separation -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.In the short description, edit the first sentence to state whether domain separation is supported or not and add the application name. Keep the conkeyref at the end that describes domain separation.Domain separation is supported for AI agents in the AI Agent Studio. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
          • AI Agent Analytics dashboard -- Track the AI agent use and efficiency gain on your instance through the AI Agent Analytics dashboard. The dashboard can reveal trends in how AI agents are used to improve the time to resolution and the number of tasks closed.
          • Run results page -- Learn about agentic evaluation runs and the meaning behind different evaluation scores from the agentic evaluation results page.
        • Model Context Protocol Client -- The ServiceNow Model Context Protocol Client (MCP Client) enables you to access the Model Context Protocol tools that are hosted externally and published using an MCP Server in the ServiceNow AI Agent Studio.
          • Exploring Model Context Protocol Client -- The Model Context Protocol (MCP) is a standardized client-server protocol that enables AI applications to discover and interact seamlessly with external tools, data sources, and services. MCP facilitates communication between an AI host application (like AI Agent Studio), an MCP Client embedded in the host, and one or more MCP Servers that expose specific capabilities such as tools.
          • Configuring Model Context Protocol Client -- Configure the MCP Client to execute agentic workflows with AI agents and mapped tools.
            • Install Model Context Protocol Client -- Install the MCP Client application on your ServiceNow instance to enable using the tools from the MCP Server in AI agents.
            • Adding an MCP Server in AI Agent Studio -- An MCP Server hosts the APIs and tools required by an AI application, enabling it to receive and process calls from MCP Clients to govern ingress traffic and to promote secure and efficient access to tools. Adding an MCP Server in the AI Agent Studio helps you to leverage the Model Context Protocol as a tool in an AI agent.
            • Model Context Protocol tool -- Add a Model Context Protocol tool to an AI agent in the AI Agent Studio so that your users can access the MCP Server.
            • Test an AI agent -- Analyze the performance of an AI agent with a Model Context Protocol tool added to it to verify that it functions the way that you defined it.
            • Model Context Protocol Client reference -- Find more information about user roles, tables, and the different properties that are installed with the Model Context Protocol Client application.
        • Autonomous Workforce -- AI specialists in your Autonomous Workforce are designed to handle high-volume, routine requests end to end, giving your team room to focus on the tasks only people can solve.
          • Explore -- Learn more about Autonomous Workforce and review the benefits AI specialists can provide for different users in your organization.
            • General guidelines -- AI specialists, like other agentic AI, benefit from strategic planning for testing, deploying, and monitoring performance. Learn guiding principles to help your AI specialists achieve their highest chances of success.
            • Domain separation -- Domain separation is unsupported for Autonomous Workforce.
            • Multilingual support -- AI specialists can respond to users in multiple languages.
          • Configure -- Configure the name, profile icon, capabilities, assignment groups, tasks, and language proficiencies of AI specialists in AI Agent Studio.
            • Configure in AI Agent Studio -- Configure your AI specialists in your autonomous workforce in AI Agent Studio.
              • Profile -- Modify the profile of an AI specialist in AI Agent Studio to set its name, description, roles, and assignment groups.
              • Tasks -- Select tasks that an AI specialist can perform in the new AI Agent Studio.
              • Preview an AI specialist -- Run a preview of your AI specialist in the new AI Agent Studio on a single record to preview how it works and verify it matches your intentions.
            • Configure in the legacy AI Agent Studio -- Configure your AI specialists in your autonomous workforce in the legacy AI Agent Studio.
              • Profile -- Modify the profile of an AI specialist in the legacy AI Agent Studio to set its name, description, roles, and assignment groups.
              • Tasks -- Select tasks that an AI specialist can perform in the legacy AI Agent Studio.
              • Preview an AI specialist -- Run a preview of your AI specialist in the legacy AI Agent Studio on a single record to preview how it works and verify it matches your intentions.
            • Assigning work -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
              • Manually assign work -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
              • Create an assignment rule -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
              • Configure AWA -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
          • Use -- AI specialists are autonomous, hierarchical AI agents designed to serve as team members who can accomplish complex tasks. Onboard AI specialists to your team to use AI for role-based automation.
            • Use in AI Agent Studio -- Onboard and view the performance and activity of AI specialists in AI Agent Studio.
              • View performance -- Review the performance analytics of an AI specialist to track their task execution success. You can use the analytics to tune the AI specialist to suit your business needs.
              • View activity -- View the task execution history of an AI specialist in the new AI Agent Studio to track where and when it plans and attempts executions. You can also give feedback on its performance.
              • Manage access -- Control workspace access, user roles, and publishing settings for your AI specialist and its copies configured for specific teams.
              • Create a copy -- Create a new copy of an AI specialist to configure different settings for different assignment groups.
              • Deactivate an AI specialist -- Deactivate an AI specialist in AI Agent Studio so that it no longer acts on records.
            • Use in the legacy AI Agent Studio -- Onboard and view the performance and activity of AI specialists in the legacy AI Agent Studio.
              • View performance -- Review the performance analytics of an AI specialist to track their task execution success. You can use the analytics to tune the AI specialist to suit your business needs.
              • View activity -- View the task execution history of an AI specialist in AI Agent Studio to track where and when it plans and attempts executions. You can also give feedback on its performance.
              • Manage access -- Control workspace access, user roles, and publishing settings for your AI specialist and its copies configured for specific teams.
              • Create a copy -- Create a copy of an AI specialist to configure different settings for different assignment groups
              • Deactivate an AI specialist -- Deactivate an AI specialist in the legacy AI Agent Studio so that it no longer acts on records and lists.
          • Reference -- Reference for Autonomous Workforce provides additional information about the roles and performance metrics associated with AI specialists.
            • AI Specialist Manager role -- Reference for Autonomous Workforce provides additional information about the roles and performance metrics associated with AI specialists.
            • Performance metrics -- Reference for Autonomous Workforce provides additional information about the roles and performance metrics associated with AI specialists.
      • Autonomous Workforce -- AI specialists in your Autonomous Workforce are designed to handle high-volume, routine requests end to end, giving your team room to focus on the tasks only people can solve.
        • Explore -- Learn more about Autonomous Workforce and review the benefits AI specialists can provide for different users in your organization.
          • General guidelines -- AI specialists, like other agentic AI, benefit from strategic planning for testing, deploying, and monitoring performance. Learn guiding principles to help your AI specialists achieve their highest chances of success.
          • Domain separation -- Domain separation is unsupported for Autonomous Workforce.
          • Multilingual support -- AI specialists can respond to users in multiple languages.
        • Configure -- Configure the name, profile icon, capabilities, assignment groups, tasks, and language proficiencies of AI specialists in AI Agent Studio.
          • Configure in AI Agent Studio -- Configure your AI specialists in your autonomous workforce in AI Agent Studio.
            • Profile -- Modify the profile of an AI specialist in AI Agent Studio to set its name, description, roles, and assignment groups.
            • Tasks -- Select tasks that an AI specialist can perform in the new AI Agent Studio.
            • Preview an AI specialist -- Run a preview of your AI specialist in the new AI Agent Studio on a single record to preview how it works and verify it matches your intentions.
          • Configure in the legacy AI Agent Studio -- Configure your AI specialists in your autonomous workforce in the legacy AI Agent Studio.
            • Profile -- Modify the profile of an AI specialist in the legacy AI Agent Studio to set its name, description, roles, and assignment groups.
            • Tasks -- Select tasks that an AI specialist can perform in the legacy AI Agent Studio.
            • Preview an AI specialist -- Run a preview of your AI specialist in the legacy AI Agent Studio on a single record to preview how it works and verify it matches your intentions.
          • Assigning work -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
            • Manually assign work -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
            • Create an assignment rule -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
            • Configure AWA -- You can assign work to an AI specialist in one of three ways, depending on your current work assignment procedures.
        • Use -- AI specialists are autonomous, hierarchical AI agents designed to serve as team members who can accomplish complex tasks. Onboard AI specialists to your team to use AI for role-based automation.
          • Use in AI Agent Studio -- Onboard and view the performance and activity of AI specialists in AI Agent Studio.
            • View performance -- Review the performance analytics of an AI specialist to track their task execution success. You can use the analytics to tune the AI specialist to suit your business needs.
            • View activity -- View the task execution history of an AI specialist in the new AI Agent Studio to track where and when it plans and attempts executions. You can also give feedback on its performance.
            • Manage access -- Control workspace access, user roles, and publishing settings for your AI specialist and its copies configured for specific teams.
            • Create a copy -- Create a new copy of an AI specialist to configure different settings for different assignment groups.
            • Deactivate an AI specialist -- Deactivate an AI specialist in AI Agent Studio so that it no longer acts on records.
          • Use in the legacy AI Agent Studio -- Onboard and view the performance and activity of AI specialists in the legacy AI Agent Studio.
            • View performance -- Review the performance analytics of an AI specialist to track their task execution success. You can use the analytics to tune the AI specialist to suit your business needs.
            • View activity -- View the task execution history of an AI specialist in AI Agent Studio to track where and when it plans and attempts executions. You can also give feedback on its performance.
            • Manage access -- Control workspace access, user roles, and publishing settings for your AI specialist and its copies configured for specific teams.
            • Create a copy -- Create a copy of an AI specialist to configure different settings for different assignment groups
            • Deactivate an AI specialist -- Deactivate an AI specialist in the legacy AI Agent Studio so that it no longer acts on records and lists.
        • Reference -- Reference for Autonomous Workforce provides additional information about the roles and performance metrics associated with AI specialists.
          • AI Specialist Manager role -- Reference for Autonomous Workforce provides additional information about the roles and performance metrics associated with AI specialists.
          • Performance metrics -- Reference for Autonomous Workforce provides additional information about the roles and performance metrics associated with AI specialists.
      • Agentic workflows -- Agentic workflows are AI‑driven workflow orchestrations that use one or more AI agents to achieve a specific outcome. They go beyond single‑step automation by dynamically planning, executing, and adapting actions based on context, data, and intermediate results.
        • In-product agentic AI -- Dedicated spaces in workspaces and in the Core UI enable you to use agentic workflows directly in record forms. You can view agentic workflow progress and previous executions, and you can answer follow-up questions for ones that require human supervision.
          • Enable the in-product experience -- Enable the AI Workflows panel and UI actions for agentic workflows on forms in the Core UI and workspaces to track agentic AI executions.
          • Interactive View in the Core UI -- Add the Interactive View Experience component to a page variant to display agentic AI processes on a record.
        • Platform agentic workflows -- You can use the available Platform agentic workflows to achieve business outcomes with self-executing autonomous AI agents.
          • Analyze task trends -- Use the Platform Analyze task trends agentic workflow to detect recurring task patterns and root causes and get recommendations to prevent them from happening in future.
          • Classify tasks -- Use the Platform Classify tasks agentic workflow to gather relevant information about tasks automatically and make decisions about priorities and assignments.
          • Generate my work plan -- Use the Platform Generate my work plan agentic workflow to create personalized work plans for currently assigned work.
          • Generate resolution plan -- Use the Platform Generate resolution plan agentic workflow to fetch task record details, generate resolution summary steps, and update comments or work notes.
          • Help optimize team productivity -- Use the Platform Help optimize team productivity agentic workflow to gather relevant information about tasks automatically and make decisions about priorities and assignments.
          • Identify ways to improve service -- Use the Platform Identify ways to improve service agentic workflow to analyze feedback, performance metrics, and historical trends that identify areas for service improvement.
          • Investigate problems -- Use the Platform Investigate problems agentic workflow to perform root cause and risk assessments so that you can create an actionable resolution plan for a problem.
          • email-task --
          • Process images for new tasks -- Use the Platform Process images for new tasks agentic workflow to convert images to actionable tasks.
          • Process task closure -- The Process task closure agentic workflow reviews open tickets to identify ones eligible for closure, then guides a human agent through reviewing and closing.
          • Propose survey responses -- Use the Platform Propose survey responses agentic workflow to assist requesters in completing surveys.
      • AI specialists -- AI specialists are autonomous AI units within the ServiceNow Autonomous Workforce. Each AI specialist is purpose‑built to perform a specific job function and deliver complete workflow outcomes, working within your organization’s existing governance, identity, and access controls.
    • Creating AI user experiences -- Deliver AI capabilities to your users with the ServiceNow Otto panel, ServiceNow Otto for Virtual Agent, and on mobile.
      • Chatting with AI -- ServiceNow Otto is the conversational AI experience across the ServiceNow AI Platform. ServiceNow Otto provides a natural language interface that makes it easier to look for information, complete a task, get help with work, or interact with AI-powered experiences.
      • Assistant Designer -- Assistant Designer is the central workspace for creating, configuring, testing, and managing assistants and their conversational experiences. Administrators use it as a single place to define an assistant's knowledge sources, capabilities, behavior, and deployment channels.
      • AI indicators on form fields -- The AI indicator is a badge that identifies form fields containing content generated or updated by an AI agent in Core UI and configurable workspaces.
    • Extending AI with external systems and providers -- Connect to large language model (LLM) providers through the Generative AI Controller and integrate AI agents with external tools and services using the Model Context Protocol (MCP).
      • Generative AI Controller -- Use Generative AI Controller to integrate your ServiceNow applications with third-party large language models (LLMs) and manage how generative AI requests are governed, protected, and logged.
        • Exploring Generative AI Controller -- Learn how Generative AI Controller works as the control and visibility layer for all generative AI requests across your ServiceNow applications, what it controls, and how it integrates with third-party LLM providers.
          • Domain separation and Generative AI Controller -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.In the short description, edit the first sentence to state whether domain separation is supported or not and add the application name. Keep the conkeyref at the end that describes domain separation.Domain separation is supported for Generative AI Controller. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
        • Configuring Generative AI Controller -- Configure Generative AI Controller providers and capabilities.
          • Installing Generative AI Controller -- The Generative AI Controller application (sn.generative.ai) is automatically installed with ServiceNow AI applications.
          • Configuring API credentials for generative AI capabilities -- Configure the credentials and connections for your preferred generative AI service provider to integrate third-party generative AI on the ServiceNow AI Platform.
            • Amazon Bedrock -- Configure your API credentials to use AWS Bedrock as your LLM provider for Generative AI Controller capabilities.
            • Azure OpenAI -- Configure your API credentials to use Azure OpenAI as your LLM provider for Generative AI Controller capabilities.
            • Google AI Studio -- Configure your API credentials to use Google AI Studio as your LLM provider for Generative AI Controller capabilities.
            • Google Vertex AI -- Configure your API credentials to use Google Vertex AI as your LLM provider for Generative AI Controller capabilities.
            • IBM watsonx -- Configure your API credentials to use IBM watsonx Granite models as your LLM provider for Generative AI Controller capabilities.
            • OpenAI -- Configure your API credentials to use OpenAI as your LLM provider for Generative AI Controller capabilities.
            • Generic LLM -- Use a generic LLM connector to connect an external AI provider to Generative AI Controller to use generative AI capabilities in your instance.
          • Configure a generic large language model (LLM) connector -- Connect an external LLM to the ServiceNow AI Platform by using a generic LLM connector. With a connector, you can write your own prompts to send to the LLM and create your own generative AI capabilities.
          • Set a provider for a generative AI capability -- Configure LLM providers for Generative AI Controller at the backend level. For most use cases, configure capabilities using AI Admin Hub.
          • Select a model for Amazon Bedrock -- Choose which large language model (LLM) to use with Amazon Bedrock for custom skills.
          • Configure small talk filters -- Redirect users to different Virtual Agent topics if small talk, such as greetings, expressions of gratitude, complaints, or requests to close, are detected in conversations.
          • Configure AI search answers capability for web search -- AI web search is a OneExtend capability that enables end users to perform web searches and receive AI-powered answers. The capability supports multiple AI providers and integrates with virtual assistants and workflows.
          • Enable recursive summarization for large inputs -- Use recursive summarization to break down the requests to the large language models (LLMs) into smaller pieces so that you can maintain the context for generative AI capabilities.
          • Enable Dynamic Translation for capabilities in Generative AI Controller -- Use Dynamic Translation to add multiple language support for generative AI capabilities to support users who speak languages other than English.
          • Disable Dynamic Translation for LLM Virtual Agent conversations -- Enable dynamic translation of chat messages into English before they are sent to the large language model in generative AI topics to support users who speak other languages.
          • Configure rate limiting for providers -- Configure rate limiting to control the traffic flow to the one_extend request by restricting the number of requests that can be made within a certain time frame.
          • Bring your own key for third-party AI provider integration -- The bring-your-own-key (BYOK) feature enables you to use your own API credentials from supported cloud AI providers, such as Azure OpenAI, Amazon Bedrock, and Google Gemini, to run generative AI skills and AI agents.
            • Configure a custom resource path for BYOK models -- Enter a custom resource path in your bring-your-own-key (BYOK) model configuration so that Generative AI Controller can connect to AI service providers that use a different web address than the default.
        • Reference for Generative AI Controller -- Reference topics provide information about Generative AI Controller tables, and properties.
      • Model Context Protocol Client -- The ServiceNow Model Context Protocol Client (MCP Client) enables you to access the Model Context Protocol tools that are hosted externally and published using an MCP Server in the ServiceNow AI Agent Studio.
        • Exploring Model Context Protocol Client -- The Model Context Protocol (MCP) is a standardized client-server protocol that enables AI applications to discover and interact seamlessly with external tools, data sources, and services. MCP facilitates communication between an AI host application (like AI Agent Studio), an MCP Client embedded in the host, and one or more MCP Servers that expose specific capabilities such as tools.
        • Configuring Model Context Protocol Client -- Configure the MCP Client to execute agentic workflows with AI agents and mapped tools.
          • Install Model Context Protocol Client -- Install the MCP Client application on your ServiceNow instance to enable using the tools from the MCP Server in AI agents.
          • Adding an MCP Server in AI Agent Studio -- An MCP Server hosts the APIs and tools required by an AI application, enabling it to receive and process calls from MCP Clients to govern ingress traffic and to promote secure and efficient access to tools. Adding an MCP Server in the AI Agent Studio helps you to leverage the Model Context Protocol as a tool in an AI agent.
          • Model Context Protocol tool -- Add a Model Context Protocol tool to an AI agent in the AI Agent Studio so that your users can access the MCP Server.
          • Test an AI agent -- Analyze the performance of an AI agent with a Model Context Protocol tool added to it to verify that it functions the way that you defined it.
          • Model Context Protocol Client reference -- Find more information about user roles, tables, and the different properties that are installed with the Model Context Protocol Client application.
      • MCP Server Console -- MCP Server Console enables secure and governed access to functionality on a ServiceNow instance for AI applications with Model Context Protocol (MCP) servers. MCP servers extend ServiceNow AI Platform functionality into any external MCP client and employee experience over the Model Context Protocol.
        • Explore -- Learn about how you can use Model Context Protocol (MCP) servers to allow AI applications to access data and perform actions on a ServiceNow instance.
        • Configure -- Create a Model Context Protocol (MCP) server and configure the tools and inputs it exposes to MCP clients.
          • Create a server -- Create a Model Context Protocol (MCP) server and configure which tools it exposes to MCP clients.
          • Creating tools -- You can create tools from various tool categories to expose ServiceNow capabilities to Model Context Protocol (MCP) clients from MCP servers.
          • Create an app -- Build, register, and display user interfaces along with your tool's logic with MCP apps. This allows you to implement and manage interactive interfaces for your tools that can be displayed by MCP clients.
          • Monitoring dashboard -- Explore MCP Server monitoring dashboard to review the performance and usage of the MCP servers and tools in a specific time frame.
          • Create an AI ACL -- Create the necessary AI Access Control List (ACL) for the component to be called externally.
          • Check a Subflow or Action compatibility -- After establishing the ACL, publish the component and check the compatibility staging table.
          • View MCP server logs -- Troubleshoot MCP server connections and tool calls by enabling logging for MCP servers and reviewing the logs.
        • Connect -- Connect to a Model Context Protocol (MCP) server from an MCP client by creating an OAuth inbound integration and configuring the client with the server details.
        • Reference -- Reference topics include information about MCP Server Console roles, tables, and more.
          • Installed components -- Several types of components are installed with activation of the MCP Server Console application, including tables and user roles.
          • Model Context Protocol Server Console tools -- Use the following tools that are available by default with Model Context Protocol Server Console depending on the applications installed on your instance, such as ServiceNow Otto for CSM or ServiceNow Otto for ITSM.
          • AI skill support in MCP Server Console -- MCP Server Console supports creating tools for Model Context Protocol (MCP) servers from a subset of AI skills.
          • Knowledge Graph schema support in MCP Server Console -- MCP Server Console supports creating tools from several preconfigured Knowledge Graph schemas, each suited to different types of queries.
          • Domain separation and MCP Server Console -- If any conkeyrefs are broken, re-add them from the doc/source/reuse/domain-separation/domain-separation-overview.dita file.Domain separation is supported for MCP Server Console. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.
      • Agentic Usage Overview Dashboard -- Monitor usage from inbound agentic connections to MCP servers from the Agentic Usage Overview Dashboard.
    • Analyzing AI effectiveness -- Measure the performance and adoption of AI capabilities on your instance to identify what is working and where to improve.
      • AI analytics -- AI Admin Center consolidates analytics for generative AI skills, AI agents, and assistants into a single monitoring experience.
      • Conversation Insights -- The ServiceNow Conversation Insights application is designed to deliver Inferred customer satisfaction (CSAT) scores, with underlying factors that can help improve CSAT actionability.
        • Exploring Conversation Insights -- Learn how Conversation Insights can help you to augment conversation insights with AI-based Inferred customer satisfaction (CSAT) scores and factors.
        • Install Conversation Insights -- If you have the admin role, you can install the Conversation Insights application (sn_aci).If the application does NOT include demo data or it does NOT install related applications and plugins, delete or revise the following sentence:The application includes demo data and installs related ServiceNow Store applications and plugins, if they aren’t already installed.
        • Conversation Insights reference -- The following topics provide additional information about the features and properties installed with Conversation Insights.
      • Conversation Improvement Themes -- The Conversation Improvement Themes application helps to transform Conversation Evaluators evaluations that are part of AI Control Tower into long-term performance insights by analyzing conversation quality data over time.
        • Explore -- The Conversation Improvement Themes application helps to transform conversation evaluations into long-term performance insights.
        • Activate -- Activate the Conversation Improvement Themes application to analyze conversation quality.
        • Use -- View performance insights using the widgets in Conversation Improvement Themes.
        • Reference -- The following topics provide additional information about the features and properties installed with Conversation Improvement Themes.
          • Components installed -- Several types of components are part of Conversation Improvement Themes, including scheduled jobs, tables, system properties, and flows.
          • Trobleshooting -- Troubleshooting steps for errors that might occur in Conversation Improvement Themes.
    • AI adoption and change management -- Apply proven change management strategies to help your workforce embrace AI capabilities and sustain adoption over time.
      • Managing change for AI adoption -- A structured organizational change management approach helps users understand, embrace, and effectively leverage AI capabilities in their daily work.
    • Solving installation and configuration issues -- Use this checklist to address issues or gaps in your AI configuration.
    • Machine learning and natural language capabilities -- The ServiceNow AI Platform includes non-generative AI capabilities that use machine learning and natural language processing to automate tasks, classify data, and enable natural interactions. These capabilities include Natural Language Understanding (NLU), Natural Language Query (NLQ), Predictive Intelligence, and Task Intelligence.
      • (Legacy) Natural Language Understanding -- ServiceNow Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions.
        • (Legacy) Exploring Natural Language Understanding -- ServiceNow Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions.
        • (Legacy) Model management -- Manage your NLU model's life cycle in the NLU Workbench. Model management phases guide you through the iterative process of building, testing, and publishing your model.
          • (Legacy) Creating models -- Creating models is the first step to taking advantage of Natural Language Understanding (NLU) in your instances. Create models for Virtual Agent and AI Search in the NLU Workbench.
            • (Legacy) Create an NLU model from blank -- Create a Natural Language Understanding (NLU) model from scratch. Start with an empty model to have full control over the model's content.
            • (Legacy) Create an NLU model from a CSV file -- Upload a CSV or XLSX (Excel Workbook) file containing utterances and their intents to create a Natural Language Understanding (NLU) model. Use this method to quickly create models from your data or other exported models.
            • (Legacy) Create an NLU model using a pre-built model -- Use the prebuilt Natural Language Understanding (NLU) models in the NLU Workbench to create a new one.
            • (Legacy) Duplicate an NLU model -- Duplicate an existing Natural Language Understanding (NLU) model to create a new one. Duplicating a model copies the settings and contents of the original model, including its default test set.
            • (Legacy) Export an NLU model -- Export a Natural Language Understanding (NLU) model to create a CSV file of the intents and utterances. You can then use the CSV file to edit, share, and import.
            • (Legacy) Add an NLU model to an update set -- Use update sets to move your Natural Language Understanding (NLU) models from one instance to another. Update sets include all records needed for your model to function on the target instance.
            • (Legacy) Delete an NLU model -- Delete a Natural Language Understanding (NLU) model permanently.
          • (Legacy) Build and train your model -- After creating a model, build the model's content by adding intents, entities, vocabulary, and test set utterances. Your NLU model content determines how the model responds to user inputs.
            • (Legacy) NLU intents -- Intents drive your models' responses by matching a system action to user inputs. Models with good intents help Virtual Agent and Search respond to your users accurately.
              • (Legacy) Create an NLU intent -- Create an intent for your Natural Language Understanding (NLU) model. Intents provide your model with a system action to perform when it receives user input.
              • (Legacy) Reusing intents from prebuilt NLU models -- Reuse Natural Language Understanding (NLU) intents by importing them from a prebuilt NLU model to other models. Reusing intents saves time when building your models.
              • (Legacy) Import an NLU intent -- As you create intents for your Natural Language Understanding (NLU) model, you can also import and reuse intents from other models in the same application scope. Reusing intents saves time when building new models.
              • (Legacy) Resolve intent issues -- Use the issue cards to identify intents that have conflicts, need reviewing, or need more utterances. Resolving intent issues ensures the intents in your Natural Language Understanding (NLU) models work properly.
            • (Legacy) NLU entities -- Entities provide your model with additional context when receiving user input. Add entities to your utterances and intents to improve the predictions of your Natural Language Understanding (NLU) model.
              • (Legacy) Create a simple entity -- Create one or more simple entities from words in your utterance examples. An entity is an object of, or context for, an action.
              • (Legacy) Create a mapped entity -- Create an entity mapped to a vocabulary source, or to a list of values you manually create for the entity. Mapped entities can help provide multiple values the model can use as context when interpreting utterances.
              • (Legacy) Create a pattern entity -- Create a pattern entity from a word or phrase with repeatable patterns, such as email addresses and phone numbers. These patterns help the system to recognize similar utterances based on the patterns.
              • (Legacy) Create a system-derived entity -- Create a custom entity that's derived from a default system entity such as date, time, duration, or location.
              • (Legacy) Create an open-ended entity -- Use an open-ended entity when you want to improve intent prediction accuracy. Open-ended entities help your model focus on the context of the utterances.
              • (Legacy) Import entities -- Reuse entities that you have created across your other Natural Language Understanding (NLU) models. Importing entities saves time and helps improve the intents in your model.
              • (Legacy) Using regular expressions in entities -- Learn how to use regular expressions in your NLU entities to establish patterns that help the system locate, match, and manage text.
            • (Legacy) NLU vocabulary -- Use NLU vocabulary items to help the system recognize the various ways your users express their requests. Use vocabulary sources to help the system recognize objects in tables or lists, such as names of conference rooms or catalog items.
              • (Legacy) Create a regular vocabulary item -- Add a word or phrase that your users might use, and match that vocabulary item to a synonym. Your model uses the synonym during intent prediction.
              • (Legacy) Create a pattern vocabulary item -- Use regular expression (regex) encoding to establish a pattern format for vocabulary items such as email addresses, phone numbers, and record naming conventions. You can create your own patterns for the vocabulary data in your instance.
              • (Legacy) Create a list vocabulary source -- Create a list of words or phrases to act as a vocabulary source. The values in the list source are replaced by the synonym if they are detected in a user utterance.
              • (Legacy) Create a table vocabulary source -- Use the values from a ServiceNow table as a vocabulary source. Your Natural Language Understanding (NLU) models use your provided synonym to interpret utterances that contain values from the chosen source fields of the table.
              • (Legacy) Sync a table vocabulary source -- Synchronize your table vocabulary sources to obtain the latest changes to the ServiceNow source table. Synchronizing your vocabulary sources ensures your NLU models have the latest values when predicting intents.
              • (Legacy) Pre-built vocabulary -- Use ServiceNow pre-built vocabulary for software and hardware terms so the system recognizes their multiple variations in utterances.
            • (Legacy) Test set creation and management -- Use the default test set of your NLU model to test the model's performance and accuracy. Manage your test set over time by building or updating its content in the NLU Workbench.
            • (Legacy) Train and try your NLU model -- Train and try your model iteratively so that its intents and entities are validated, compiled, and saved to your model.
            • (Legacy) Test panel feedback -- When testing your NLU model on the Try model section of the test panel, use this feature to provide feedback on the model's intent predictions.
          • (Legacy) Test and publish your model -- Assess the performance of your NLU model to identify areas for improvement. Then publish your model to make it available to other applications such as Virtual Agent.
            • (Legacy) Test your model -- Test your Natural Language Understanding (NLU) model against its default test set. Testing helps determine how your model is performing with the current content.
            • (Legacy) Publish your NLU model -- Publish your Natural Language Understanding (NLU) model to activate it and make it available for use in other applications that consume NLU.
            • (Legacy) Compare draft and published versions of your NLU model -- Compare a draft trained Natural Language Understanding (NLU) model to its most recent published version. Test and review the changes to make sure that your draft model will have increased performance.
          • (Legacy) Irrelevance detection in NLU -- Keep Virtual Agent chats focused with Irrelevance detection. Use the Irrelevance detection feature to train your NLU model to avoid making predictions for utterances that are not relevant.
          • (Legacy) Tune your model -- On your model's overview in NLU Workbench, open the Tune your model phase to review and incorporate user utterances from the Expert Feedback Loop.
          • (Legacy) NLU model settings -- Change your NLU model's name, description, or confidence threshold on the Settings page of the model overview.
        • (Legacy) Multilingual model management -- Use multilingual Natural Language Understanding (NLU) models for the system to understand user input in several languages. The NLU Workbench helps you manage and maintain a consistent structure for content across languages to provide a unified experience.
        • (Legacy) Virtual Agent and NLU Workbench integration -- Virtual Agent administrators can access and update their NLU models from within the Virtual Agent Designer user interface.
        • (Legacy) NLU Workbench - Advanced Features -- NLU Workbench - Advanced Features expands the functionality of NLU Workbench to help you manage and improve your models.
          • (Legacy) Install NLU Workbench - Advanced Features -- You can install the NLU Workbench - Advanced Features application (com.snc.nlu.workbench.advanced) if you have the admin role.
          • (Legacy) Multi-model Batch Testing -- Test multiple Natural Language Understanding (NLU) models against a large set of utterances to evaluate the performance of the models. Add test sets, test multiple models, and see test results.
            • (Legacy) Create a test set -- To create or add to an NLU test set, you can upload a file of test utterances matched with correct intents. Use the test set to assess the performance of your model.
            • (Legacy) Run a multi-model batch test -- Test multiple Natural Language Understanding (NLU) models against a test set. Evaluate the quality of your models and refine them to improve intent prediction.
          • (Legacy) Cross-model Conflict Review -- Identify conflicting intents within or across models so you can take corrective actions, resolve such conflicts, and improve your NLU model performance.
          • (Legacy) NLU Model Performance -- Use NLU Model Performance to see how well your models predicted intents in Virtual Agent (VA) based on end-user confirmation.
          • (Legacy) NLU Expert Feedback Loop -- Provide feedback on Virtual Agent chat log utterances to help the system continuously learn and to better predict user input.
          • (Legacy) Issue Auto Resolution Tuning in NLU -- Use the NLU Workbench homepage to support Issue Auto Resolution (IAR) tuning in NLU.
            • (Legacy) Issue Auto Resolution tuning options -- When you are tuning your Issue Auto Resolution model in NLU Workbench, you can adjust the output for several goals: precision, automation, or a balance of the two. Compare how your choice of tuning options affect match rate and coverage, before committing.
          • (Legacy) Intent Discovery -- Use the Intent Discovery application to help identify opportunities for incident deflection. For example, you can use it to identify which Virtual Agent conversations to activate next.
            • (Legacy) Install Intent Discovery -- You can install the Intent Discovery application (sn_nlu_discovery) if you have the admin role.If the application does NOT include demo data or it does NOT install related applications and plugins, delete or revise the following sentence:
      • Natural Language Query -- Natural Language Query (NLQ) enables you to query the data in your instance by entering plain language requests into the user interface.
        • Exploring Natural Language Query -- NLQ is a ServiceNow AI Platform feature that is active by default. Use NLQ to query the data in your instance by entering plain language requests into the user interface.
        • Using Natural Language Query -- With Natural Language Query (NLQ), you can query data in your tables by entering requests in natural, everyday language.
        • Configuring NLQ -- Enhance your users' query experience by supplementing NLQ with words and terms used in your environment. Review your users' actual requests in the NLQ logs to find possible synonyms and shortcuts to add.
          • Create an NLQ synonym -- Add synonyms to improve the ability of NLQ to recognize the various ways your users request data. With synonyms, you can map commonly used words or terms to table columns.
          • Create an NLQ shortcut -- Create a semantic shortcut to help improve the ability of NLQ to recognize the various ways your users request data. Semantic shortcuts operate similarly to NLQ synonyms by mapping common words to columns, but for a selected table when certain conditions are met.
          • View NLQ logs -- Review NLQ logs to see how the system has handled your users' plain-language requests. Use log records from attempted requests to expand NLQ synonyms or shortcuts.
          • View NLQ Table Guesser logs -- Use the Table Guesser logs to review the CMDB tables that were picked by NLQ in response to plain-language queries.
        • Natural Language Query References -- The following components are installed with Natural Language Query.
      • Predictive Intelligence -- Predictive Intelligence is a powerful interface to train machine learning models. With Predictive Intelligence, you can improve performance, efficiency, and flexibility to your systems across multiple business units.
        • Explore Predictive Intelligence -- ServiceNow Predictive Intelligence is a platform function that provides a layer of artificial intelligence that empowers features and capabilities across ServiceNow applications to provide better work experiences.
        • Install Predictive Intelligence -- Activate Predictive Intelligence on your instance and get started with basic configuration.
        • Configure Predictive Intelligence -- Configure solution definitions for Predictive Intelligence to train, test, and monitor solution definitions
          • Database View support for Predictive Intelligence -- Use database views to join two or more tables as input for your Machine Learning (ML) solution.
          • Configuration tips for Predictive Intelligence -- If you encounter issues during your solution training and solution prediction, follow these suggested resolutions.
          • Create a custom stopwords list -- Exclude common words you want the system to ignore during training and prediction.
          • Create a word corpus -- Build a collection of words and phrases that functions as the vocabulary the system uses to compare your instance records based on their textual similarity. You can think of the word corpus as a dictionary that you want your machine-learning system to understand.
          • Quick start tests for Predictive Intelligence -- Validate that Predictive Intelligence still works after you make any configuration change such as applying an upgrade or developing an application. Copy and customize these quick start tests to pass when using your instance-specific data.
          • Activate a solution version -- Predictive Intelligence activates the most recent version of the solution when it completes training a solution. However, you can activate any previously trained solution version. Only one solution version can be active at a time, and only the active version is used when making predictions.
          • Export trained solutions to production -- Refine and test your ML solutions iteratively on a non-production instance, and then use update sets to export the changes to your production instance. This practice mitigates the risk of retraining solutions on your live production instance.
          • Configuring advanced settings for your ML solutions -- Learn about advanced settings for your Predictive Intelligence machine learning (ML) solutions. Apply optional technology and algorithms for classification, clustering, similarity, and regression capabilities.
        • Creating and training solutions -- Use one of the Predictive Intelligence (PI) frameworks to create and train machine-learning solutions. Each framework delivers a different solution type for training the system to predict, recommend, and organize data outcomes.
          • Create and train a classification solution -- Specify the records used to train a classification solution, what fields trigger a prediction, and how often you want to retrain your solution.
            • Exclude a class from prediction -- Exclude a class from prediction if its precision or coverage aren't satisfactory. Excluding a class prevents the classification model from predicting a particular output field value.
            • Exclude a class from solution training -- Exclude a class from solution training to prevent the model from ever making predictions for a particular output field class. For example, you can exclude a particular incident category from training if you plan to retire or change the category.
            • Tune a trained classification solution -- Tune the performance of a trained classification solution by configuring class level precision and coverage values.
            • Configuring target metrics for a trained classification solution -- Set values for precision, coverage, and recall statistics for a trained machine learning solution.
            • Using Group By for classification -- Use APIs to simultaneously submit multiple classification solutions for training based on the Group By field.
            • Model Explainability -- Analyze the importance of each input field to your model's predictions using model explainability. Create a Workflow Classification model that includes a graphical analysis of feature importance by executing the provided script.
            • Test time explainability -- Understand the reasons your machine learning solution made a specific prediction with Test time explainability, which returns a list of input features that influenced the prediction.
          • Create and train a similarity solution -- Create and train a machine learning solution to collect and compare your existing records to new similar records. For example, you can compare the text in an open Incident record to a resolved Incident record to reuse its resolution.
            • Update your similarity score threshold -- After you review the similarity examples provided by the system, update your solution similarity score threshold if you want the results returned by the solution to be more or less similar.
          • Create and train a clustering solution -- Group similar records into clusters so you can address them collectively or identify patterns.
          • Create and train a regression solution -- Regression solutions have been deprecated. They could be used to predict numeric outputs, such as a temperature or a stock price.
          • View solution training progress -- View your solution training progress or statistics to determine if a solution is available, or how long the next training cycle might take to complete.
            • Review classification solution statistics -- The Solution Statistics dashboard in Predictive Intelligence has been deprecated in the Xanadu release. It provided precision and coverage statistics for each class in a classification solution.
            • Review solution similarity examples -- Review the similarity examples generated during solution training to determine whether the similarity score threshold meets your business requirements.
        • Using Predictive Intelligence -- Train and use Predictive Intelligence solutions to accomplish various tasks.
        • Testing and monitoring predictions -- Evaluate the coverage and precision of your machine-learning (ML) solutions by testing them. Once deployed, track their performance over time. Improve predictions by using performance information to refine your solutions.
          • Test a classification solution prediction -- Once your machine-learning (ML) solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. In this example procedure, we use the REST API Explorer to test a classification solution prediction for incident categorization.
          • Test a similarity solution prediction -- Once your machine-learning (ML) solutions are trained, you can call on the Predictive Intelligence API to make a solution prediction. In this example procedure, we use the REST API Explorer application to test a similarity solution prediction for resolved incident recommendations.
          • Track classification prediction results over time -- Use the Prediction Results dashboard to determine if classification solution predictions are improving over time. Identify solutions that need refining or retraining.
          • Reviewing prediction errors with the Observability Dashboard -- The Observability Dashboard offers a unified view and actionable insights for errors detected in Predictive Intelligence. Use this dashboard to visualize logged errors and gain information on prediction reliability and potential problem areas.
          • Predictive Intelligence Usage Analytics dashboard -- The Predictive Intelligence Usage Analytics dashboard is a central location to understand the effectiveness and overall value of all your Predictive Intelligence solutions. View metrics for model training successes and failures. Monitor prediction statistics including breakdowns by individual model.
        • Predictive Intelligence references -- Reference pages for components of Predictive Intelligence.
      • Task Intelligence -- Task Intelligence uses machine learning to train solutions with your data and achieve important outcomes.
    • Additional resources for AI products and solutions -- If you’re looking for AI best practices, troubleshooting, or other implementation guidelines, select a feature or resource type to discover ServiceNow resources on other relevant websites.
Search documentation
Search document titles and file paths on the australia branch