Configuring security metrics in AI Control Tower

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.
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.

Parent Topic:Managing AI asset security with AI Control Tower

title	Configuring security metrics in AI Control Tower
description	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.
locale	en-US
canonical_url	https://www.servicenow.com/docs/r/australia/intelligent-experiences/gov-sec-configuring.html
release	australia
topic_type	concept
last_updated	2026-09-10
reading_time_minutes	2
keywords	ServiceNow OttoAI Agentsgenerative AIagentic AIconfigure
breadcrumb	Managing AI asset securityGovern AI assetsAI Control TowerEstablishing AI governanceEnable AI Experiences