Use agentic AI in Now Assist for Public Sector Digital Services (PSDS)
Summarize
Summary of Use agentic AI in Now Assist for Public Sector Digital Services (PSDS)
The Public Sector Digital Services (PSDS) offering in Now Assist enables administrators to use agentic AI to automate specific government service tasks. Through the AI Agent Studio, admins can configure, test, and manage AI agents using natural language and prebuilt workflows. These AI agents help streamline processes such as estimating fees for information requests and handling related administrative tasks.
Show less
Key Features
- AI Agent Studio: Provides a user-friendly interface for admins to create and manage AI agents tailored to public sector service needs.
- Use Case Example: AI agents assist government service agents by estimating fee breakdowns for information requests, recommending fee waiver approvals or rejections with explanations, and calculating total fees including any applicable waivers.
- Supported Large Language Models (LLMs): Supports multiple AI model providers including Now LLM Service, Now LLM Long Term Stable models (LTS), Azure OpenAI, Google Gemini, and Anthropic Claude on AWS. Admins control available options via AI Control Tower configurations and skill-level preferences in the Now Assist Admin console.
- Security Controls: Execution of AI agents and workflows is secured through Access Control Lists (ACLs) and user identity management. ACLs enable agents to run actions as dynamic users or AI users, ensuring secure and compliant automation.
- Autonomous AI Agent Activation: To enable autonomous operation, admins must duplicate and activate agentic workflows and individual agents, and set unique triggers for automatic invocation. Manual invocation is also supported without activating triggers.
- Azure OpenAI Recommendation: Azure OpenAI is suggested specifically for IT Service Management (ITSM) agentic workflows.
- Standalone AI Agents: Some AI agents included with Now Assist may not be part of predefined use cases but are available for use. Admins can view and manage all available AI agents.
Key Outcomes
- Automated fee estimation and decision-making reduce manual workload for government agents.
- Secure and configurable AI workflows enhance trust and compliance in public sector digital services.
- Flexible AI model integration allows organizations to choose the best LLM provider for their needs.
- Administrators have full control over AI agent activation, management, and security settings, enabling tailored automation aligned with organizational policies.
- Improved efficiency and accuracy in handling information requests contribute to better citizen service delivery.
Use AI 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 Now Assist 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.
| 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 Now Assist and security controls that are important considerations for using agentic AI.
Supported Large Language Models
-
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®.
- For the Now LLM Service updates, see Now LLM Service updates.
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 Now Assist AI agents
Considerations for running the autonomous AI Agents
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 may be AI agents installed with the Now Assist application that are not used in use cases. 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.