This feature is a legacy feature and may be deprecated soon. If you still have access to this feature, you can find this in Advanced Settings. Otherwise, if you cannot see this feature in your account, you will not be able to use it moving forward. If you wish to build a multi-agent system, we recommend using the Workforce feature instead.
Decide how errors should be managed when they occur:
Use Default Settings: Follow your workspace’s standard error handling rules
Use Custom Settings: Create specific error handling instructions just for this Sub-agent
Custom settings are particularly useful when a Sub-agent needs special treatment for retries, escalations, or alternative workflows when something goes wrong.
Write clear directions for when and how the parent Agent should use this Sub-agent:
Example: "Use this Research Sub-agent whenever you need to gather competitive information or market data. Provide specific search terms and the type of information needed."
Good instructions ensure the parent Agent knows exactly when to call on this Sub-agent and what information to provide.
Create a standardized format for requests sent to the Sub-agent:
Example: "Please research {{topic}} and focus on {{specific_aspect}}. The information will be used for {{purpose}}."
Variables like {{topic}} will be filled in by the parent Agent when making requests. This creates consistency and ensures all necessary context is included with each request.
When your agent calls a sub-agent, a live activity card appears in the parent agent’s conversation timeline. This replaces the previous static spawn receipt and gives you real-time visibility into what the child agent is doing.
While the sub-agent is working, the activity card shows how many steps the sub-agent has completed and which tool it is currently using. This updates live as the sub-agent progresses through its task.
Click the activity card to expand the full conversation history for that sub-agent run. The expanded view shows each tool step in order, along with tool outputs and any error messages if the run failed.
Use the expandable view to debug a failed sub-agent run — it shows exactly which step failed and what error was returned.