Using agentic workflows in Now Assist for PSDS

  • Release version: Xanadu
  • Updated July 31, 2025
  • 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 Using agentic workflows in Now Assist for PSDS

    ServiceNow’s Now Assist for Public Sector Digital Services (PSDS) includes an agentic workflow calledHelp manage public information requeststhat automates synthesizing related information requests and calculating associated fees. This workflow helps organizations efficiently estimate fees, assess fee waiver requests, and apply fees to cases, improving management of public information requests.

    Show full answer Show less

    Key Features

    • Help manage public information requests workflow: Analyzes fee waiver justifications, validates them against predefined rules, identifies similar past cases, and estimates fee breakdowns.
    • AI Agents involved:
      • Information Request Playbook Fee Estimation Agent – calculates subtotal fee estimates based on similar requests.
      • Information Request Playbook Fee Waiver Review Agent – recommends approval or rejection of fee waiver requests and calculates total fees with waivers applied.
    • Activation and configuration: AI agents must be enabled via the Status field in the Define availability screen. The workflow and agents are read-only by default and require duplication and activation to run autonomously.
    • AI model providers supported: Now LLM Service, Now LLM Long Term Stable models (LTS), Azure OpenAI, Google Gemini, and Anthropic Claude on AWS.
    • Security controls: Access Control Lists (ACLs) enable secure execution of AI agents and workflows using dynamic or AI user identities, with Run As capabilities.
    • Workflow triggers: Workflows can be triggered automatically with unique triggers or invoked manually.

    Practical Use for ServiceNow Customers

    By leveraging this agentic workflow, customers can automate and standardize the processing of public information requests, including fee estimation and waiver evaluation. This reduces manual effort, ensures consistent application of predefined rules, and improves accuracy in fee calculations. Customers can customize AI models and access controls to align with their organizational policies and compliance requirements.

    Next Steps

    • Duplicate and activate the agentic workflow and associated AI agents to enable autonomous operation.
    • Configure AI model preferences in the Now Assist Admin console.
    • Set up unique triggers for automatic invocation or opt for manual execution.
    • Ensure security implementations are in place via ACLs to safeguard AI agent execution.
    • Explore additional AI agents in your instance or from the AI Agent Marketplace to expand capabilities.

    Automate the process of synthesizing similar information requests, associated fees, and apply those fees to cases​ using the Help manage public information requests agentic workflow, as part of the Public Sector Digital Services AI Agent Collection application. ​

    The following table lists the skills and agents associated with this workflow. These AI agents work to arrive at a subtotal fee estimate, a recommendation for whether a fee waiver request should be approved or rejected, and a total fee estimate with the fee waiver, if applicable.

    Important:
    In the Define availability screen for the AI agent, make sure that the Status field is enabled to activate the AI agent.
    Table 1. Available workflows for Public Sector Digital Services AI Agent Collection
    Agentic Workflow name Description Available AI agents
    Help manage public information requests
    • 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.
    1. Information Request Playbook Fee Estimation Agent
    2. Information Request Playbook Fee Waiver Review Agent
    Looking for an AI agent?
    • 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 on your instance, see Find AI agents.
    • To find agents that might not be installed on your instance, visit the AI Agent Marketplace on the ServiceNow Store.
    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 to define which options are available, then set the skill-level preferences in the Now Assist Admin console. For more information, see .

    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.