---
sourceDocument: Xanadu Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/xanadu/intelligent-experiences

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Flow action

# Add a flow action to an AI agent {#ariaid-title1}

* Release version: Xanadu
* 
* Updated January 30, 2025
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Add a flow action to an AI agent in AI Agent Studio. Define the flow action to use it as a reusable operation in automating the ServiceNow AI Platform features without having to write code.

## Before you begin

When an AI agent uses a flow action tool, the user the AI agent is running as must pass the ACL of the flow action. Ensure that the security configurations for the flow action are met by the AI agent and agentic workflow. For more information, see [Security for AI agents](https://servicenow-prod.fluidtopics.net/QbjR~ixuVaGgxQKuXyJjXg "Implement security controls for AI agents and agentic workflows through access control lists (ACLs) and user identities to increase alignment with the access control-based security measures in the agentic system.").

Role required: sn_aia.admin

## Procedure

1. Navigate to AllAI Agent StudioCreate and manageAI agents.
2. Open the AI agent that you want to add a flow action to and navigate to the Add tools and information section.
3. In the Add tool drop-down list, select Flow action.
4. On the form, fill in the fields.  
   {#add-flow-action-ai-agent__table_wlm_2v5_cdc__entry__2}

   | Fields | Description |
   |-|-|
   | Name | Name that you want to specify for your selected flow action. |
   | Description | Description of the flow action and what it's going to do to assist your AI agent. Note: This description is sent to the large language model (LLM). |
   | Select flow action | Existing automated process to be selected from the list. |
   | Inputs | Flow action inputs. The values are filled in by the LLM at runtime unless you specify a value override. Note: If the agent uses multiple tools, you can choose to use another tool's output as an input value override. Select the data picker icon (![Data picker icon.]()) to review the available options. |
   | Execution mode | Mode of execution for your selected flow action: * Supervised: Inputs from your live agent are required during the execution of this flow action while the AI agent runs. * Autonomous: Doesn't require any input from your live agent during the execution of this flow action while the AI agent runs. {#add-flow-action-ai-agent__ul_knh_pv5_cdc} |
   | Display output | Permission to display the output of the execution in the Now Assist panel or in Virtual Agent: * Yes * No {#add-flow-action-ai-agent__ul_jlr_tv5_cdc} |
   | Processing message | Message to display to users when the tool is running. |
   | Output transformation strategy | Style for the LLM to present the results. * None * Concise * Paragraph * Verbose |
   [Table 1. Add a flow action form]

   {#add-flow-action-ai-agent__table_wlm_2v5_cdc}
5. Select Add.  
   A flow action is added in the Flow actions list on the Add tools and information page.

*[\>]: and then


