--- sourceDocument: Zurich Conversational Interfaces sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/conversational-interfaces Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich Conversational Interfaces ft:clusterId : - convint bundleId : - convint workflow : - Platform --- # AI agents in Virtual Agent topics # AI agents in Virtual Agent topics {#ariaid-title1} Release version: Zurich Updated September 10, 2026 ![](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 AI agents in Virtual Agent topics AI agents in Virtual Agent topics enable ServiceNow customers to automate specific tasks within Virtual Agent conversations by leveraging AI-powered custom skills. These agents perform tasks such as consolidating content from knowledge base articles when invoked from a Virtual Agent topic. Show full answer Show less AI agents are accessible through the AI Connector utility in Assistant Designer, where customers can select, configure, and deploy these agents to enhance Virtual Agent interactions with AI-driven functionality. ## Using AI Agents with Virtual Agent * AI agents are selected by choosing the appropriate skill type and AI agent type within the AI Connector utility. * Tasks are defined using input mapping variables, such as specifying which knowledge base article to consolidate (e.g., `return KB00090;`). * Output mapping properties are automatically configured for each AI agent type and provide detailed information on the agent's task execution. ## Key Features * **Task Execution Tracking:** AI agents generate a complete execution plan that details the objective, tasks performed, messages sent, and tools used. * **Comprehensive Output Mappings:** Output includes execution plan ID, state, objective, state reason, messages, tasks, and tools involved, all returned in the Virtual Agent chat. * **Centralized Management:** AI agents installed on the instance can be viewed and managed, ensuring customers know which agents are available for use. ## Practical Benefits for ServiceNow Customers By integrating AI agents into Virtual Agent topics, customers can: * Automate complex tasks such as knowledge base article consolidation within chat conversations. * Enhance Virtual Agent responses with AI-generated content and insights. * Gain full visibility into the AI agent's execution details for monitoring and troubleshooting. This capability enables more intelligent, context-aware Virtual Agent interactions that improve user experience and operational efficiency. An AI agent custom skill performs a task that you pass to it from a Virtual Agent topic, such as consolidating the content of a knowledge base article. 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](https://www.servicenow.com/docs/access?context=find-ai-agents&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). An AI agent performs a task that you pass to it inside the AI Connector utility in Assistant Designer. For more information on the AI Connector utility, see [AI Connector utility](https://www.servicenow.com/docs/q_MdoxB7qezJCrEelMPzqg "Use this utility to link generative AI to custom skills for added versatility in your Virtual Agent LLM (large language model) conversations."). For example, you can use the AI agent in the AI Connector utility to get all data on a knowledge base article. The AI agent provides the article if it is available or notifies you if it can't find it. The agent also provides data on the consolidation itself by way of its output mappings. To see which AI agents are installed on your instance, see [Find AI agents](https://www.servicenow.com/docs/access?context=find-ai-agents&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US). To use the AI agent, select it from the Skill type drop-down list in the AI Connector utility, then select the AI agent's type from the Select AI agent drop-down list. For example, to have the AI agent consolidate a knowledge base article, select KB content consolidation AI agent. Define the task for the AI agent by placing a value in the Task input mapping variable. You can define a condition, or enter a script or command. For example, enter `return KB00090;` to have the AI agent retrieve that knowledge base article and consolidate its information into a reply in the Virtual Agent chat. The AI agent's output mapping properties are automatically defined when you select the AI agent type. All output mappings are returned in the chat when the AI agent completes the task. {#ai-agent-custom-skill__table_orx_d4v_lfc__entry__2} | Variable | Description | |-|-| | Execution plan ID | ID number of the execution plan. | | Execution state | Current state of the execution plan. | | Objective | Intended task for the execution plan. | | State reason | Reason for the execution plan's current state. | | Messages | List of messages sent through the execution plan. | | Execution tasks | List of tasks in the execution plan. | | Execution tools | List of tools in the execution plan. | [Table 1. AI agent output mapping properties] {#ai-agent-custom-skill__table_orx_d4v_lfc} When the AI agent performs its job, it generates the full plan showing the input and output mappings. Each plan shows the objective, all tasks performed for the objective, and any messages sent or tools used in the plan. All plans are listed in the Execution Plan \[sn_aia_execution_plan_list\] table.