Configuring the Agent step

Updated 29 September 2026

You can add an agent you have built in Agentstudio to an agentic workflow in Integration using Agent step. This topic walks you through the process of configuring Agent step.

Step 1: Sync your agent

Agents must be synced in Agent Control Tower before invoking them in an Agent step. Since syncing is not immediate, you can sync agents manually.

Go to Agent Control Tower > Manage Providers > Boomi Agent Garden.
Select the Account link, then select the Action icon > Sync Now. Syncing may take several minutes. A Success status indicates completion.

Step 2: Configure Agent step

You can configure Agent step to use an Agentstudio agent deployed to a Boomi-managed runtime cloud. If you are a part of the Bring Your Own Model Early Access program and Flex Runtime Early Access program, you can also configure Agent step to use a self-hosted agent from the Flex Runtime.

Get a Platform API token

note

Self-hosted agents in Early Access do not require a platform API token. If you are using a self-hosted agent as a part of the Early Access program, skip this step.

To invoke the agent in the Agent step, you must have a Boomi Platform API token. For more information about API tokens, refer to Adding new API Token on a user account. Platform API Token updates apply only to the selected configuration and must be associated with your Boomi username.

Configure your ingress endpoint

If your agent runs in a self-hosted runtime, you must configure your runtime’s ingress endpoint after installing a Flex runtime with an Agent workload. This is a post-install, runtime-level setting.

This action must be done before configuring Agent step. Refer to Configuring your runtime’s ingress endpoint to step-by-step guidance.

If your agent runs in a Boomi-managed runtime cloud, skip this step.

Generate a configuration

Navigate to Integration.
Open an existing process or create a new one.
Add an Agent step to your process if you haven't already.
In the Agent step, select Configure.
Select a runtime to browse your deployed agents from Control Tower. This runtime is different from where the agents are actually deployed. If you don't have access to a Boomi public cloud runtime attachment, you can select a different runtime to browse agents and generate the configuration. Refer to Browsing available agents for troubleshooting.
Select your agent. You can filter by selecting the deployment region. Self-hosted runtimes are categorized as a "Self-Hosted" region.
(Optional) Enter a Display name for your configured Agent step.
Select Generate Configuration.
Select the Runtime Type.
1. Cloud - Agent uses a Boomi-managed runtime cloud.
2. Common - Agent uses a self-hosted runtime (Early Access). Refer to Flex Runtime for details.
Enter a configuration name in the Configuration Name field, or accept the displayed default name.
(Optional) Select Return Application Error Responses to prevent failed operations from appearing in Process Reporting. This option lets you handle them directly in your processes.
Select the Authentication tab.

note
If you select a self-hosted runtime (Early Access only), skip to step 14. A Platform API key is not required.
Select Click to Set and enter the API token you generated in Get a Platform API token.
Select Apply. After you save the configuration, you can find it in the Component Explorer and open it to configure a few other settings, such as error behavior, document archiving, tracking, and caching.
1. Error Behavior - If checked, failed operations are not reported in Process Reporting, allowing you to act on them in your process.
2. Platform Username and Platform API Token - These are automatically populated based on the account used to create the Agent step. You do not need to configure these fields manually.
  
  caution
  Modifying the Platform Username and Platform API Token fields could disrupt the connection between the Agent step and the agent.
3. Advanced Configuration (Timeouts) - You can set connection and read timeouts (in milliseconds) for the Agent step so that the process does not wait indefinitely.
Select Ok.
Select Save.

note

Session logs are not available in Agent Control Tower for agent sessions in an Integration process.

Review important details about agentic workflow capabilities when using the Bring Your Own Model feature (Early Access). Refer to Using your own models with agents: Important considerations.

Where Agent step components are stored

When you configure an Agent step within a process, Boomi stores the related configuration components in an Agents component group in the Component Explorer. If the process resides within a folder, the Agents folder is created inside that same folder.

The first time you add an Agent step, Boomi generates a root-level Agents component group that holds the connection details for the agent provider. For Boomi agents, this connection component cannot be edited.

Within the Agents component group, each configured agent gets its own grouping containing its specific configuration components. If you configure the same agent multiple times within a process, all of those configurations are stored together.

Agent configurations can be reused across different processes. If you configure a new Agent step in a process located in a different folder, Boomi creates a new Agents folder in that directory for the configuration unless you select an existing configuration component to reuse.

caution

Do not copy Agent connection components to another account. Connections are tied to the account in which they were created, so the copied component will include the original account information in the component URL, and the Agent step will not run.

Since you cannot edit this component, delete it and reconfigure your step to let the system recreate it with the correct information.

Next steps

Configure the rest of your process to support your agentic workflow. Refer to Integration process design patterns for agentic workflows for details.