Important considerations for using ServiceNow Otto for IT Service Management (ITSM) agentic AI

  • Release version: Australia
  • Updated March 12, 2026
  • 2 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Important considerations for using ServiceNow Otto for IT Service Management (ITSM) agentic AI

    ServiceNow Otto enables IT Service Management (ITSM) agentic AI agents to autonomously complete tasks through agentic workflows. This functionality leverages supported Large Language Models (LLMs) to power generative AI skills and automate processes within your ServiceNow instance. Understanding configuration, security, and activation requirements is essential to successfully deploy and operate these AI-driven workflows.

    Show full answer Show less

    Key Features

    • Supported Large Language Models: You can utilize Now LLM Service, Azure OpenAI, Google Gemini, or Anthropic Claude on AWS as AI model providers. Configuration of available models and skill preferences is managed through AI Control Tower and the AI Admin Hub console.
    • Security Controls: AI agents and agentic workflows operate under strict security via Access Control Lists (ACLs) and user identities. The Run As capability allows these agents to execute actions as either dynamic users or AI users. Role masking governs user access, requiring specific roles to be included in security configurations when restricting access to particular user groups.
    • Agentic Workflow Activation: By default, agent workflows and AI agent records are read-only. To enable autonomous operation:
      • Duplicate the agentic workflow to create an editable version.
      • Activate the duplicated agentic workflow and all contained AI agents.
      • Activate unique triggers to invoke workflows automatically, unless manual invocation is preferred.
    • Model Recommendation: Azure OpenAI is recommended for ITSM agentic workflows for optimal performance.
    • Standalone AI Agents: Some AI agents may be present independently of agentic workflows. Customers can identify all available agents within their instance to determine usage.

    Practical Guidance for ServiceNow Customers

    • Configure AI model providers and define skill preferences carefully to align with your organizational needs using AI Control Tower and AI Admin Hub.
    • Implement security settings rigorously, ensuring ACLs and role masking are properly configured to maintain controlled, secure agent execution.
    • To enable autonomous AI agent operation, duplicate and activate workflows and agents, and set unique triggers unless manual execution is desired.
    • Consider using Azure OpenAI as your LLM provider for agentic workflows to leverage recommended capabilities.
    • Review and manage standalone AI agents in your instance to maintain clarity on your AI resources and usage.

    Use the IT Service Management AI agents within an agentic workflow to complete tasks autonomously.

    Supported Large Language Models

    Note:

    Security implementation considerations

    Enable security implementation to execute AI agents and agentic workflows through Access Control Lists (ACLs) and user identities. ACLs provide the Run As capability to let agents and agentic workflows execute actions either as a dynamic user or as an AI user. For more information, see Implement access control in AI agents

    Agentic workflows and their AI agents use role masking to determine which users can access them. Ones installed with your applications have specific roles that come included with the application. If you select Users with specific roles for user access, you must configure the security controls to include these roles. For the instructions to change the security controls, see Define security controls for an agentic workflow.

    AI agents use role masking to determine which users can access them. Ones installed with your applications have specific roles that come included with the application. If you select Users with specific roles for user access, you must configure the security controls to include these roles. For the instructions to change the security controls, see Define security controls for an AI agent.

    Considerations for running the autonomous AI Agents

    Important:
    By default, all agent workflow and AI agent records are read-only.

    To run the AI agents autonomously, you must first duplicate the agentic workflow, and then proceed with the following steps:

    • Activate the agentic workflow.
    • Activate all agents within the agentic workflow.
    • Activate the trigger to invoke the agentic workflow automatically. The triggers for each agentic workflow must be unique. If you prefer to invoke it manually, activating the trigger isn’t necessary.
    • Azure OpenAI is recommended for ITSM agentic workflows. For information on Large Language Models (LLMs) for AI agents and agentic workflows, see Large language models on the ServiceNow AI Platform®.

    Standalone AI agents

    There might be AI agents installed on your instance that are not used in agentic workflows. To learn how to see all agents that are available to you, see Find AI agents.