Important considerations for using Now Assist for IT Service Management (ITSM) agentic AI
Summarize
Summary of Important considerations for using Now Assist for IT Service Management (ITSM) agentic AI
Now Assist for IT Service Management (ITSM) enables customers to use AI agents within autonomous agentic workflows to complete ITSM tasks efficiently. This functionality supports multiple large language model (LLM) providers, allowing flexibility in AI model selection and control through configuration settings.
Show less
Key Features
- Supported Large Language Models: Customers can choose from Now LLM Service, Now LLM Long Term Stable (LTS) models, Azure OpenAI, Google Gemini, or Anthropic Claude on AWS as AI providers.
- Configuration Controls: Available LLM options and skill preferences are managed via AI Control Tower and the Now Assist Admin console, enabling tailored AI behavior.
- Security Implementation: Access Control Lists (ACLs) and user identity management ensure secure execution of AI agents and workflows. The Run As capability lets agents act as dynamic or AI users.
- Role Masking and Privileges: Role masking limits AI agent privileges during execution. Pre-defined roles assigned to AI agents and workflows require corresponding security and data access configurations when restricting user access.
- Agent Activation and Workflow Management: To run AI agents autonomously, duplicate the read-only agentic workflow, activate the workflow, enable all associated agents, and activate unique triggers for automatic invocation. Manual invocation is also supported without activating triggers.
- Standalone AI Agents: Some AI agents may be available outside of agentic workflows. Customers can view installed agents in their instance or explore additional agents via the AI Agent Marketplace on the ServiceNow Store.
Key Outcomes
- Customers gain autonomous AI-driven ITSM task execution, improving efficiency and responsiveness.
- Flexible AI provider options and configuration controls allow customization to organizational requirements.
- Robust security measures preserve control over AI agent actions and data access.
- Clear procedures for activating and managing agentic workflows ensure reliable autonomous operation.
- Access to a broad range of AI agents supports diverse ITSM automation needs.
Use the IT Service Management AI agents within an agentic workflow to complete tasks autonomously.
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
Role masking enables users to limit the roles and privileges of agentic workflows during tool execution. Agentic workflows and their AI agents that get installed with Now Assist applications are assigned pre-defined roles. If you select Users with specific roles for user access, you must configure the security controls to include these roles. Data access settings must also include these roles. For the instructions to change the security controls, see Define security controls for an agentic workflow.
Role masking enables users to limit the roles and privileges of AI agents during tool execution. AI agents that get installed with Now Assist applications are assigned pre-defined roles. If you select Users with specific roles for user access, you must configure the security controls to include these roles. Data access settings must also 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
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 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.