--- sourceDocument: Zurich Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/intelligent-experiences Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Understand AI agents # Understand AI agents {#ariaid-title1} Release version: Zurich Updated October 24, 2025 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 Understand AI agents The Now Assist AI agents application within the ServiceNow AI Platform enables secure use of your data, workflows, and integrations to automate and enhance incident and case management. AI agents dynamically adapt their actions based on evolving conditions to stay focused on achieving their objectives efficiently. Show full answer Show less The AI Agent Studio provides guidance for leveraging AI agents effectively, while the AI Agent Orchestrator centrally manages coordination between multiple AI agents to handle complex workflows seamlessly. ## Key Features * **AI Agent Orchestrator:** Acts as a central management system that coordinates collaboration among AI agents, enabling effective task sharing and smooth transitions regardless of workflow origin. * **Task Coordination \& Execution:** Ensures AI agents perform tasks in the correct sequence within multi-step workflows. * **Dynamic Decision-Making:** Invokes AI models dynamically based on specific scenarios for improved accuracy and performance. * **Enterprise Integration:** Seamlessly integrates with ServiceNow workflows, CMDB, and third-party APIs to support end-to-end automation. * **Policy \& Governance Enforcement:** Maintains compliance and security standards by enforcing governance rules across AI agent actions. * **ReAct Prompt and Scheduling Mode (Route):** Combines reflection and planning prompts to streamline execution. The scheduling mode enables asynchronous, parallel execution among agents to reduce latency and boost performance. * **Dynamic Orchestrator:** Optimizes agent selection for workflows, especially when more than 8 to 10 AI agents are available, enhancing workflow performance and accuracy. * **User Impersonation:** Executes AI agent actions as the logged-in user in the ServiceNow Otto panel, maintaining clear audit logs. This supports accountability and troubleshooting by recording which AI agent approved actions. * **Virtual Agent Integration:** Can be enabled for AI agents to allow interaction and visibility of transactions in the AI agent guided setup. ## Practical Benefits for ServiceNow Customers * Enables robust automation of complex, multi-step workflows through coordinated AI agent collaboration. * Improves operational efficiency by dynamically adapting AI agent actions and reducing execution latency. * Enhances governance and compliance by embedding policy enforcement and detailed activity logging within AI workflows. * Facilitates seamless integration with existing ServiceNow systems and third-party tools for comprehensive automation. * Supports transparency and accountability through user impersonation and logging features, aiding in issue resolution and audit processes. The Now Assist AI agents application is designed to securely leverage your data, workflows, and integrations directly within the ServiceNow AI Platform. AI agents can dynamically adjust their actions based on the progress and changing conditions of incidents or cases to help ensure that they stay focused on achieving their objectives. ## AI agents Orchestrator {#understand-na-aia__section_ef1_htr_bhc} The AI Agent Studio guides users in leveraging AI agents effectively, while AI Orchestrator ensures seamless collaboration among them. The AI agent Orchestrator is a central management system that coordinates AI agents to ensure that they collaborate effectively to complete complex workflows. It can also retrieve missing context from users when needed. AI agents operate iteratively, seeking assistance from the Orchestrator if they encounter difficulties. The Orchestrator enhances inter-agent communication and centralizes coordination. The Orchestrator allows AI agents to share information effectively and transition tasks seamlessly, regardless of where the process originates. As a result, the Orchestrator is essential for managing intricate workflows, facilitating real-time adaptability, and efficient task delegation among agents. The role of Orchestrator in AI Agent Studio: 1. Task Coordination \& Execution: manages the interaction between multiple **AI agents**, ensuring that tasks are executed in the correct sequence. 2. Dynamic Decision-Making: Can invoke AI models dynamically based on the scenario. 3. Seamless Integration with Enterprise Systems: Works with ServiceNow workflows, CMDB, and third-party APIs to enable end-to-end automation. 4. Handling Multi-Step Workflows: Enables chained execution of AI-driven tasks among multiple AI Agents. 5. Policy \& Governance Enforcement: Enforces governance rules to ensure that AI agents adhere to compliance and security standards. {#understand-na-aia__ol_e4m_bnt_bhc} The Orchestrator works with ReAct prompt, where the previous reflection prompt has been merged with the planning prompt for a streamlined execution experience improving the efficiency and visibility of planner actions. With the ReAct prompt, a scheduling mode called Route has been introduced that enables asynchronous, parallel tool execution within agents to reduce latency and improve performance when an agent needs assistance from another agent during the execution process. ## Dynamic Orchestrator for agentic workflows {#understand-na-aia__section_f3x_324_xfc} The dynamic orchestrator helps map the right agents to the user's agentic workflow to provide better performance and accuracy. When there are more than the ideal 8 to 10 AI agents available for an agentic workflow, then the dynamic orchestrator helps identify the agents that need to be considered for executing that agentic workflow in the planning phase. ## User impersonation in AI agents {#understand-na-aia__section_ckd_hhm_g2c} The agentic workflow executes tools as the logged-in user in the ServiceNow Otto panel. Any operations that are performed within the tool in this flow are also executed as the logged-in user. After impersonation is enabled, testing an AI agent uses the instance-level impersonation. Administrators can see logs with individual AI agent names as a record of who approved the agentic action in an agentic workflow. The logs help when determining a point of contact if there's an issue with the approved agentic action by the AI agent. With impersonation, the fulfiller in the ServiceNow Otto panel and the requester in Virtual Agent can see the transactions recorded in the name of the AI agent that performed the agentic workflow execution. Note: Virtual Agent can be turned on only for AI agents at the Define availability section in the AI agent guided setup. For more information, see [Create an AI agent](https://www.servicenow.com/docs/xqCwuTfKJR788l~2LxWosA "Create an AI agent in AI Agent Studio to solve problems for your users and coordinate with other AI agents while executing the agentic workflows.").