Delegates are other saved agents this agent hands parts of a request to. The agent's model splits each request among them, each delegate works on its part as a subagent, and the agent combines their results. In harness runs each delegate shows as a subagent in the trace. Every delegate makes its own model calls, so delegated requests cost more.
{% if not ui_read_only %}
Add a harness as a delegate
A harness delegate runs its part on that harness, with the harness's own tools and sandbox. On Agent Harnesses it works in that run's workspace; in the playground it uses the workspace set on the delegate (its agent harness settings), or else the folder the UI runs in. Agent delegates run on their own models with MemoRizz's tools. Mixing both works well: send code and file work to a harness, research and writing to an agent.
{% endif %}
{% if delegation_has_plan %}
This agent follows a fixed plan set in code. The plan is kept as it is; these settings choose which agents it can use and how their results are combined.
{% endif %}