--- sourceDocument: Australia Build workflows sourceDocumentLink: https://www.servicenow.com/docs/r/build-workflows Release : - australia ft:locale : - en-US ft:publication_title : - Australia Build workflows ft:clusterId : - crworkflow bundleId : - crworkflow workflow : - Creator --- # Use an AI agent action # Use an AI agent action {#ariaid-title1} * Release version: Australia * * Updated March 12, 2026 * * ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 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 Use an AI agent action The "Use an AI agent" action in Flow Designer enables ServiceNow customers to run AI agents within their flows, leveraging AI to automate tasks and generate outputs for use later in the workflow. This action is available as part of the Flow Designer Gen AI spoke and requires theNow Assist AI agentsplugin. It empowers users with theflowdesigneroradminroles to integrate AI-driven automation into their business processes efficiently. Show full answer Show less ## Key Features * **AI Agent Input Configuration:** Users select the AI agent to run, which must be created and configured beforehand using the Now Assist AI agents plugin. * **Support User:** For supervised mode, specify a support user who reviews and authorizes the AI agent's output. This user must meet defined security controls and have appropriate roles. * **Objective:** Provide clear text instructions for the AI agent to guide its task. * **Execution Mode:** Choose between *Autonomous mode* (runs without user input) and *Supervised mode* (requires user approval or interaction). * **Wait for Completion:** Optionally pause the flow until the AI agent finishes processing and returns results. * **Expected Outputs:** Define the data objects the AI agent is expected to return, enabling downstream use of AI-generated data in the flow. * **Conversation Label and Context Memory:** Customize the identification of AI interactions and provide contextual information to improve AI output relevance. ## Outputs and Integration The action provides several outputs that can be used in subsequent flow steps: * **Execution Plan Record:** Contains the full details of the AI agent execution, including objectives, tasks, messages, and tool executions. * **Agent Output:** The dynamic object holding the AI agent's returned data based on the expected outputs. * **Agent Message:** Text message response from the AI agent. * **Agent Status:** Indicates success or failure of the AI agent run. ## Practical Example An example use case involves the **Incident resolution details AI agent** , which requires the **ServiceNow Otto for ITSM** plugin and the Resolution notes generation skill enabled. In this supervised mode example, the flow pauses for the support user to interact with the Now Assist panel and approve or provide input. Once approved, the flow continues and uses the AI-generated outputs to send an email message. ## Benefits for ServiceNow Customers * Seamlessly incorporate AI capabilities into workflows to enhance automation and decision-making. * Maintain control and security by using supervised mode with designated support users. * Improve process efficiency by automatically generating outputs like incident resolution details. * Leverage contextual memory and clear objectives to tailor AI agent performance to specific business needs. Use flow data to run an AI agent and configure the expected agent output for use later in the flow. ## Roles and availability {#use-an-ai-agent-action__section-subscription-roles} Available as a Flow Designer Gen AI spoke action, which requires the Now Assist AI agents plugin. Users with the flow_designer or admin role can add an action to a flow and define configuration details. ## Inputs {#use-an-ai-agent-action__section-inputs} Provide a value for each input that your action needs. To add dynamic values, you can also select data pills using the pill picker.{#use-an-ai-agent-action__inputs-description} AI Agent : Data type: Reference The AI Agent that you want to use in this flow. You must install the Now Assist AI agents plugin and create and configure an AI agent. For information about installing the Now Assist AI agents plugin, see [Install ServiceNow Otto AI Agents](https://www.servicenow.com/docs/access?context=install-ai-agents-plugins&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). For information about creating an AI agent, see [Create an AI agent](https://www.servicenow.com/docs/access?context=configure-next-best-action-agent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Support User : Data type: Reference The user who is contacted by Now Assist to review and authorize the AI agent's work when the AI agent runs in supervised mode. Select a user who meets the security criteria defined in the AI security controls. If the AI agents is configured to accept a dynamic user, select a user that has the roles necessary to run the AI agent. For more information about the security controls of an AI agent, see [Define security controls for an AI agent](https://www.servicenow.com/docs/access?context=define-sec-controls-aia&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). For information about turning on the Now Assist panel, see [Activate the ServiceNow Otto panel standard chat](https://www.servicenow.com/docs/access?context=activate-now-assist-panel&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Objective : Data type: String The text directions sent to the AI agent. Wait for completion : Data type: True/False Option to pause the flow until the AI agent finishes running and provides output values. Execution mode : Data type: Choice Option to run an AI agent with or without user input or approval. In Autonomous mode, the action runs the AI agent without any user input or approval. In Supervised mode, the action requires user input or approval to run the AI agent. Expected outputs : Data type: Dynamic Object List of output objects that the AI agent is expected to return. Each expected output is an object that has a label, name, and a data type value. You can use the expected outputs to gather data from the AI agent and then use that data elsewhere in the flow. Conversation label : Data type: String The name that identifies the conversation about running the AI agent in the Now Assist panel. For information about activating the Now Assist panel, see [Activate the ServiceNow Otto panel standard chat](https://www.servicenow.com/docs/access?context=activate-now-assist-panel&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Context Memory : Data type: String The context information that you want to send to the AI agent. This context helps determine what output values the AI agent produces. ## Outputs {#use-an-ai-agent-action__section-outputs} You can use these outputs as inputs for other items.{#use-an-ai-agent-action__outputs-description} Execution Plan Record : Data type: Reference The record containing the Objective, Execution Tasks, Messages, and Tools Executions run by the AI agent. Agent Output : Data type: Dynamic Object The object containing the list of expected output values generated by the AI agent. Agent Message : Data type: String The message returned by the AI agent. Agent Status : Data type: String The run status of the AI agent. The AI agent returns success when it runs or failure when it doesn't run. ## Use Incident resolution details AI agent {#use-an-ai-agent-action__example_ark_w45_khc} This example requires installing the ServiceNow Otto for IT Service Management (ITSM) plugin and turning on the Resolution notes generation skill. In this example, the Use an AI agent action is configured to use the Incident resolution details AI agent in a supervised mode. The objective lists data that will help the AI understand the resolution of an incident. Since this example runs in supervised mode, the flow pauses until the support user interacts with the conversation generated in the Now Assist panel. After the support user provides the necessary response, the flow continues running the action and provides it output values. The flow uses these output values to send an email message.