Standalone AI Agents in Public Sector Digital Services

  • 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 Standalone AI Agents in Public Sector Digital Services

    The Standalone AI Agents within the Public Sector Digital Services (PSDS) AI Agent Collection application enable organizations to automate specific tasks effectively. Ensuring the Status field is enabled in the Define availability screen is crucial for activating these agents.

    Show full answer Show less

    Key Features

    • Information Request Playbook Fee Estimation Agent: Analyzes fee waiver justifications and estimates associated fees for information requests.
    • Retrieves similar case records to aid in fee calculations.
    • Communicates detailed fee breakdowns including sub-total estimates and fee waiver recommendations.
    • Compatibility with various AI model providers such as Azure OpenAI, Google Gemini, and Anthropic Claude on AWS.
    • Configuration Controls in AI Control Tower allow customization of options and skill-level preferences in the Now Assist Admin console.
    • Access Control Lists (ACLs) enable secure execution of AI agents and workflows, providing the capability to run as dynamic or AI users.

    Key Outcomes

    To run AI agents autonomously, customers must duplicate the agentic workflow, activate it, and ensure all agents and triggers are uniquely set. Manual invocation of triggers is optional. The use of Azure OpenAI is recommended for ITSM workflows, enhancing the overall automation process in public sector digital services.

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

    Important:
    In the Define availability screen for the AI agent, make sure that the Status field is enabled to activate the AI agent.

    The following table describes the available AI agents in the Now Assist for Public Sector Digital Services (PSDS) application.

    Table 1. Available standalone AI Agents for the Public Sector Digital Services AI Agent Collection
    AI Agent name Description
    Information Request Playbook Fee Estimation Agent
    • Analyzes fee waiver justification from applicant for an information request case record, and validates justification against predefined rules
    • Outlines the steps required to estimate the fees associated with an information request
    • Retrieves similar case records and allows user to exclude any from the fee calculation
    • Estimates and communicates fee breakdown associated with an information request case record based on similar request queries and request details from the user
    • Communicates sub-total estimate, fee waiver recommendation, and total with fee waiver.
    Note:
    Verify that AI Search is enabled on the instance before configuring the agents.

    There might be AI agents installed with the Now Assist application that are not used in agentic workflows. To learn how to see all agents that are available to you, see Find AI agents.

    Note:

    You can use Now LLM Service, Now LLM Long Term Stable models (LTS), Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all Now Assist 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 Now Assist Admin console. For more information, see Large language models on the ServiceNow AI Platform®.

    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 Now Assist 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 Select the LLM for AI agents and agentic workflows.

    For more information on configuring AI Agents, see Activate an AI Agent in Public Sector Digital Services AI Agent Collection.