Use agentic AI in ServiceNow Otto for Public Sector Digital Services (PSDS)

  • Release version: Zurich
  • Updated November 6, 2025
  • 3 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 Use agentic AI in ServiceNow Otto for Public Sector Digital Services (PSDS)

    The Public Sector Digital Services (PSDS) AI Agent Collection in ServiceNow Otto enables administrators to use standalone, configurable AI agents to automate specific tasks within government service operations. These agents are managed through the AI Agent Studio, part of the PSDS offering, allowing configuration, testing, and management via natural language and prebuilt workflows. The primary goal is to streamline processes such as fee estimation and information requests.

    Show full answer Show less

    Key Features

    • AI Agent Studio: Provides administrators with an interface to configure, test, and manage AI agents using natural language commands and predefined workflows.
    • Use Cases in PSDS:
      • Estimate fee breakdown for information requests: Assists government agents in calculating subtotal fees, determining fee waiver approvals or rejections with explanations, and computing total fees including any waivers.
    • Supported Large Language Models (LLMs): Now LLM Service, Azure OpenAI, Google Gemini, and Anthropic Claude on AWS can be used as AI model providers for all generative AI skills and agents. Configuration options are controlled via AI Control Tower and AI Admin Hub.
    • Security Controls: Access Control Lists (ACLs) and user identities secure AI agents and workflows, enabling execution with Run As capabilities (dynamic or AI user). Role masking restricts access to authorized users, and specific roles included with applications must be configured in security settings.
    • Agentic Workflows Activation: To run AI agents autonomously, duplicate the default read-only agentic workflows, then activate the workflow, all included agents, and the unique trigger for automatic invocation. Manual invocation is optional.
    • Recommendations: Azure OpenAI is recommended for ITSM-related agentic workflows.
    • Standalone AI Agents: Some AI agents may exist outside agentic workflows. Administrators can view and manage these standalone agents separately.

    Key Outcomes

    • Automated handling of government service tasks like fee estimation, improving accuracy and efficiency.
    • Streamlined configuration and management of AI agents via an intuitive studio, lowering administrative overhead.
    • Robust security implementation ensuring AI agent actions comply with organizational access policies.
    • Flexibility to run AI agents autonomously or manually, tailored to operational needs.
    • Support for multiple LLM providers offers adaptability based on organizational preferences and compliance requirements.

    Use standalone agents to achieve specific automated outcomes with the Public Sector Digital Services AI Agent Collection application. ​

    AI Agents are configurable through the AI Agent Studio. The AI Agent Studio is available to administrators as part of the ServiceNow Otto for Public Sector Digital Services (PSDS) offering. The AI Agent Studio allows admins to configure, test, and manage AI agents using natural language and prebuilt workflows. These agents can automate tasks like fee estimation and information request handling.

    This table describes the use cases in ServiceNow Otto for Public Sector Digital Services (PSDS).
    Table 1. Use cases powered by Agentic AI in Public Sector Digital Services
    Use case Description
    Estimate fee breakdown for an information request Helps government service agents determine the fee breakdown for an information request by working to arrive at a subtotal fee estimate, a recommendation for whether a fee waiver request should be approved or rejected, including reasons for any rejection, and a total fee estimate, with the fee waiver, if applicable.

    Find information such as the Large Language Models (LLM) supported in ServiceNow Otto and security controls that are important considerations for using agentic AI.

    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.

    For information on the standalone Public Sector Digital Services AI agents, see Standalone AI Agents in Public Sector Digital Services.