Module settings reference

Select the agent you want to use or click the Create agent button to create a new agent.

If you want to create a new agent:

Agent's tools are the . When you send a task to the agent, it will use reasoning powered by the AI provider's model to identify what the agent needs to do. Then, the agent looks into its context information. The agent's context contains the names and descriptions of all that are available to them. Based on the information and the context, the agent runs the that are available to it.

If you want the agent to input data to the before running, you need to set up scenario inputs with descriptions for each parameter. Agent will identify how to use the input data based on the description.

Similarly, if you want the agent to receive data from a , you have to set up scenario outputs.

The agent gets access to in two places: in the agent settings and in the Run an agent module settings. Agent-level tools are provided to the agent in the agent settings. The agent has the agent-level tools always available, regardless of the module in which you put the agent.

The list of agent-level tools in the module settings is read-only. If you need to update the agent-level tools, you need to change them in the agent settings.

In Additional tools, you can add that the agent has available only when running through the module.

You can specify a custom thread ID to keep all the communication with the agent in the same communication thread. This allows you to maintain the agent's context with a history of messages that you sent to the agent.

You can use additional system instructions to customize the agent's context for the current module. In addition, you can use mapping in the additional instructions. This allows you to create dynamic context information for the agent based on other data from the . This can be quite powerful.

The Messages fields contain the tasks you are sending to the agent. You can send multiple user messages through one module operation.

Enable this option to forward the agent's response to the specified URL.

Sometimes, the agent might take a while to respond. If the Run an agent module doesn't get a response in 180 seconds, it would output the ModuleTimeoutError and stop the . If you think the agent could take a long time to respond, enable this option.

In the Webhook URL field, specify a webhook URL. If you don't have a webhook ready:

When the Run an agent module runs, it replies immediately with a notification that will forward the agent's reply to the specified webhook. When the agent finishes its tasks, the Custom webhook trigger receives its reply.