Agentic AI for the Operational Technology Manager

  • Release version: Zurich
  • 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 Agentic AI for the Operational Technology Manager

    The Operational Technology (OT) Manager Foundation AI agent uses agentic workflows to autonomously complete tasks related to managing OT device data. This capability is designed to streamline operations by automating data import, validation, and integration into the OT Configuration Management Database (CMDB).

    Show full answer Show less

    Key Features

    • Import OT Device Spreadsheet into OT CMDB Workflow: Automates the import process by mapping device inventory spreadsheets to the OT staging table, validating records, remediating invalid entries, and importing validated data into the CMDB.
    • Supported Large Language Models: The AI agents and generative AI skills can utilize Now LLM Service, Azure OpenAI, Google Gemini, or Anthropic Claude on AWS as AI model providers, configurable via AI Control Tower and AI Admin Hub.
    • Security Implementation: Execution of AI agents and workflows is governed through Access Control Lists (ACLs) and user identity management to ensure secure operations.
    • Agent Activation and Execution: To run AI agents autonomously, customers must duplicate and activate agentic workflows, activate all included AI agents, and configure unique triggers for automatic invocation. Manual invocation is also supported without activating triggers.
    • Role Masking and Access Control: Access to agentic workflows and AI agents is controlled through role masking. Customers must configure security controls to grant access to users with specific roles associated with these workflows.
    • Standalone AI Agents: Some AI agents may exist independently of workflows and can be discovered and managed separately.

    Practical Benefits for ServiceNow Customers

    • Automates and simplifies the management of OT device inventory and CMDB data, reducing manual effort and errors.
    • Provides flexibility in AI model providers to align with organizational preferences and compliance requirements.
    • Ensures secure and controlled use of AI agents through role-based access and ACLs, maintaining governance and data protection.
    • Enables autonomous AI agent operation with customizable triggers for seamless integration into existing IT workflows.

    The Operational Technology (OT) Manager Foundation AI agent operates within agentic workflows to complete tasks autonomously.

    Table 1. Available agentic workflows for OTM AI agent collection
    Agentic workflow name Description Available AI agents
    Import OT device spreadsheet into OT CMDB With the Import OT device spreadsheet into OT CMDB agentic workflow, you can do the following:
    • Import the device inventory spreadsheet and map data to the OT staging table
    • Validate OT staging table records, remediate invalid records, and import all validated records into the Configuration Management Database (CMDB)
    		 OT Excel import task AI agent
    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 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.