Configuring agentic conversations in Virtual Agent

concept brazil Updated Sep 10, 2026 5 min read agentic-conversations-vad.md
Raw file servicenow.com

When you query a Virtual Agent, it reasons, plans, and executes across a wide variety of options. The Virtual Agent can use AI agents, virtual agent topics, conversational actions and subflows, catalogs, KB articles, custom skills, and any ServiceNow Otto for Virtual Agent supported skills to help you.

  • If specific agents are available for the assistant to perform user tasks or subtasks, they are used.
  • If no specific agent is available for the task or subtask, the system automatically employs the Search Agent to discover answers or appropriate skills within the system. This is based on the assistant's scope.
  • If skill execution is required, the system automatically executes the discovered skills.
  • The system plans and orchestrates execution among multiple agents, skills, and QnA to accomplish complex tasks.

Note: When a Virtual Agent conversation is triggered, any updates or comments in the record's work notes display as the AI agent rather than the user who initiated the conversation.

Examples of AI agent behavior for user utterances

The examples will consider the following available example resources in the system:

Agents

Skills/Topics

KB Articles

Check IT Ticket status agent

Email Agent

Meeting scheduling Agent

Order coffee

Order food

Order laptop

Order accessories

Spam

ESPP policy
**Scenario 1: Multiple questions from KB articles**

Utterance: How do I avoid spam? How do I detect it?

  • Non-agentic response: Produces a single mixed answer.

    [Omitted image "utterance-qna.png"] Alt text: Non-agentic response.

  • Agentic response: Breaks it into two questions and provides a better answer for each one of them.

    [Omitted image "utterance-agentic1.png"] Alt text: Agentic response part1.[Omitted image "utterance-agentic2.png"] Alt text: Agentic response part2.

Scenario 2: Multiple skills with slot filling

Utterance: Hey, order a coffee for me, preferably dark roast and something to eat, maybe a pizza?

  • Non-agentic response: Produces a single answer. Mostly listing all matching available skills. No auto-execution since it matched multiple skills.

    [Omitted image "utterance2-qna.png"] Alt text: Non-agentic response.

  • Agentic response: Breaks it into two distinct tasks, order coffee and order food/pizza. Executes one after another, completing the entire user request.

    [Omitted image "utterance2-agentic1.png"] Alt text: Agentic response part1.[Omitted image "utterance2-agentic2.png"] Alt text: Agentic response part2.[Omitted image "utterance2-agentic3.png"] Alt text: Agentic response part3.

Scenario 3: Complex utterance with a combination of skills, agents, and QnA

Utterance: I am going on PTO tomorrow. Get my expense report and my IT ticket status. Send a summary of the expense report to John Jacob and the details on ticket status to Robert Williams, informing them of my PTO and requesting them to work on them.

  • Non-agentic response: Produces a single answer. It lists all matching available skills. No auto-execution will take place since it matched multiple skills.

    [Omitted image "utterance3-qna.png"] Alt text: Non-agentic response.

  • Agentic response: Breaks it into multiple distinct tasks, reasons and plans, understands the dependencies, and executes one after another, completing the entire user request using output from prior actions as context as needed.

    [Omitted image "utterance3-agentic1.png"] Alt text: Agentic response part1.[Omitted image "utterance3-agentic2.png"] Alt text: Agentic response part2.[Omitted image "utterance3-agentic3.png"] Alt text: Agentic response part3.[Omitted image "utterance3-agentic4.png"] Alt text: Agentic response part4.[Omitted image "utterance3-agentic5.png"] Alt text: Agentic response part5.[Omitted image "utterance3-agentic6.png"] Alt text: Agentic response part6.

Scenario 4: Complex utterance with a combination of QnA (KB) and agent

Utterance: What is the maximum contribution amount for espp? Send an email to Robert with the details.

  • Non-agentic response: Produces a single answer and doesn’t complete or even suggest the second action since there’s no corresponding skill.

    [Omitted image "utterance4-qna.png"] Alt text: Non-agentic response.

  • Agentic response: Understands the two separate intents and executes them in sequence while using the output from the first intent to fulfill the second intent.

    [Omitted image "utterance4-agentic1.png"] Alt text: Agentic response part1.[Omitted image "utterance4-agentic2.png"] Alt text: Agentic response part2.

Halting and restarting agentic conversations

If you want to stop an agentic conversation mid-query, hover over the send icon [Omitted image "vad-send-icon.png"] Alt text: Send icon. while the agent is researching a query. The icon becomes an interrupt flow icon [Omitted image "vad-interrupt-flow-icon.png"] Alt text: Interrupt flow icon.. Select the icon and the conversation stops. A message appears: The current conversation has been stopped, but you can begin again. Enter a new query to restart the agentic conversation.

Error handling and fallback options

When the AI agent can't understand a request, encounters a system error, or a session becomes inactive, it displays a message and presents options to help you continue.

  • When ServiceNow Otto can't find an answer, it will provide options based on how the assistant was configured. Options may include:

    • Requesting a live agent
    • Creating a support request
    • Viewing office hours For example, if you ask about a topic the AI agent can't find information on, you might see a message such as: “I can’t find anything on that directly but I can help you explore other options.” Select one of the displayed options to continue.

  • Session timeout due to inactivity:

    If you stop responding during a conversation, the AI agent waits for a set period before ending the session. When a session is about to time out, you will receive a warning message. For example: “Looks like you’ve left this conversation. Would you like to keep going?”. If you want to continue, respond to resume the conversation.

    If there is no response to the warning, the session ends with a session end message. For example, “Our chat has timed out due to inactivity. Just start a new conversation whenever you’re ready. I’ll be here to help!”. You can start a new chat to continue getting help.

  • Technical errors and system timeout:

    If the AI agent encounters a backend error or can't complete a request due to a technical issue, it displays a message and presents fallback options. For example: “It looks like I’m having trouble completing your request right now because of a technical failure. But I can help you explore other options.” You can select one of the available fallback options to continue.

  • Errors during agentic tasks:

    When you ask the AI agent to complete a multi-step task on your behalf, it plans and carries out the steps automatically. If a step in the plan can't be completed, it lets you know and offers fallback options so you can decide how to proceed.

    For example, if the AI agent is creating an expense report and encounters a problem, it displays a message such as: “Unfortunately that didn’t work. But I can help you explore other options.” The fallback options available depend on your configuration.

Note: Review AI generated responses for accuracy before taking action.

Keywords AI agent
Search documentation
Search document titles and file paths on the brazil branch