Agentic AI for Operational Technology Service Management

  • Release version: Zurich
  • Updated July 23, 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 Agentic AI for Operational Technology Service Management

    The Agentic AI for Operational Technology Service Management (OTSM) enables autonomous task completion by leveraging AI agents and agentic workflows tailored for OT service processes. This functionality helps automate routine tasks such as generating knowledge base (KB) articles after OT incident resolutions, improving efficiency and knowledge retention.

    Show full answer Show less

    Key Features

    • Agentic Workflows: Predefined workflows automate specific tasks, like the "Generate OT KB articles" workflow, which creates documentation automatically post-incident resolution using contextual information.
    • AI Agents: Specialized AI agents such as the OT knowledge generator support these workflows, executing tasks without manual intervention.
    • Customization: To modify any agentic workflow, customers must duplicate the workflow, adjust settings as needed, and activate the duplicate. This ensures the base workflows remain unchanged.
    • Activation Controls: Workflows and their AI agents are inactive by default. Activation requires enabling the duplicated workflow, associated AI agents, and unique triggers for automatic invocation.
    • Role-Based Security: Access to agentic workflows and AI agents is controlled through role masking and Access Control Lists (ACLs), ensuring only authorized users can execute or modify them.
    • AI Model Support: The platform supports multiple large language models (LLMs), including Now LLM Service, Azure OpenAI, Google Gemini, and Anthropic Claude on AWS. Configuration of these models is managed via AI Control Tower and AI Admin Hub.
    • Standalone AI Agents: Instances may include AI agents not tied to workflows. Customers can review and manage these separately for additional automation opportunities.

    Practical Application for ServiceNow Customers

    ServiceNow customers can leverage the OTSM Agentic AI to automate knowledge management and incident resolution documentation, reducing manual workload and increasing operational efficiency. By activating and customizing agentic workflows, customers tailor AI-driven automation to their specific OT service management needs while maintaining strict security controls. The flexibility to choose from multiple LLM providers and configure AI model preferences ensures alignment with organizational policies and performance requirements.

    Next Steps

    • Duplicate and customize agentic workflows as needed to fit your operational requirements.
    • Activate workflows, AI agents, and unique triggers to enable autonomous execution.
    • Configure role-based access and ACLs to secure AI agent operations.
    • Manage AI model preferences through AI Control Tower and AI Admin Hub to optimize AI capabilities.

    Use the Operational Technology Service Management (OTSM) AI agent collection to complete tasks autonomously.

    Table 1. Available agentic workflows for OTSM AI agent collection
    Agentic workflow name Description Available AI agents
    Generate OT KB articles After OT incident resolution, the AI agent automatically creates a KB article with relevant contextual information. OT knowledge generator AI agent
    Important:
    To change this agentic workflow, duplicate it, adjust the settings to suit your specific needs, and activate the duplicated version of the agentic workflow instead.

    The minimum role needed to duplicate an agentic workflow is the sn_aia.admin role. By default, the OTSM agentic workflow is inactive. To use the base system agentic workflow, activate the base system trigger. To customize the agentic workflow, duplicate it.

    Important:
    Some generative AI skills, AI agents, and agentic workflows are turned on by default. For more information, see Now Assist skills, agents, and agentic workflows on by default.

    Supported Large Language Models

    Note:

    You can use Now LLM Service, Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all generative AI skills and AI agents. Use the Configuration Controls in AI Control Tower to define which options are available, then set the skill-level preferences in the AI Admin Hub console. For more information, see Large language models on the ServiceNow AI Platform®.

    Security implementation considerations

    Enable security implementation to execute AI agents and agentic workflows through Access Control Lists (ACLs) and user identities. For more information, see Implement access control in Now Assist AI agents

    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.

    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.

    Role masking

    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.