Use an AI agent action
Summarize
Summary of Use an AI agent action
TheUse an AI agentaction in Flow Designer enables ServiceNow customers to run AI agents using flow data and configure expected outputs for further use within the flow. This action is available through the Flow Designer Gen AI spoke and requires theNow Assist AI agentsplugin. It allows automation of tasks by integrating AI capabilities directly into workflows.
Show less
Key Features
- Roles and Availability: Users with the
flowdesigneroradminroles can add and configure this action in flows. - Inputs:
- AI Agent: Reference to an installed and configured AI agent (requires Now Assist AI agents plugin).
- Support User: Reference to a user who reviews and authorizes AI agent work when running in supervised mode, ensuring compliance with AI security controls.
- Objective: Text instructions describing the task for the AI agent.
- Wait for completion: Option to pause the flow until the AI agent completes its task.
- Execution mode: Choose between Autonomous (runs without user input) or Supervised (requires user approval) modes.
- Expected outputs: Define the data objects the AI agent should return for use later in the flow.
- Conversation label: Name identifying the conversation in the Now Assist panel.
- Context Memory: Additional context sent to the AI agent to improve output relevance.
- Outputs:
- Execution Plan Record: Contains details of the AI agent’s execution including objectives, tasks, and messages.
- Agent Output: The dynamic object with the AI agent’s generated outputs.
- Agent Message: The message returned by the AI agent.
- Agent Status: Indicates success or failure of the AI agent run.
Practical Example
Using the Incident resolution details AI agent (requires Now Assist for ITSM plugin and Resolution notes generation skill), a flow can be configured to run the AI agent in supervised mode. The flow pauses to allow the support user to review and authorize the AI agent’s input via the Now Assist panel. After user interaction, the flow resumes and uses the AI-generated outputs, for example, to send an email notification.
Why It Matters
This action empowers ServiceNow customers to integrate AI-driven automation in workflows with flexibility for supervision and security. It enhances operational efficiency by enabling AI agents to process objectives, produce structured outputs, and interact with users when needed, all within the Flow Designer environment.
Use flow data to run an AI agent and configure the expected agent output for use later in the flow.
Roles and availability
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
Provide a value for each input that your action needs. To add dynamic values, you can also select data pills using the pill picker.
- 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 Now Assist AI agents. For information about creating an AI agent, see Create an AI agent.
- 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. For information about turning on the Now Assist panel, see Activate the Now Assist panel standard chat.
- 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 Now Assist panel standard chat.
- 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
You can use these outputs as inputs for other items.
- 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
This example requires installing the Now Assist 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.