tournament
Spawn multiple AI agents with distinct roles to answer the same prompt, then collect and compare their responses via tagged broadcast.
Instructions
Spawn N children with different roles on the same prompt, then collect their answers via a tagged broadcast and return a comparison.
roles: comma-separated role names. Predefined: skeptic, generator,
critic, archivist, synthesizer, explorer, executor. Custom names allowed
(child gets generic instruction). Each role gets a distinct system
prompt addendum encoding its mindset.
Each child is told to broadcast its final output as exactly: [] [] Parent polls signals every 2s for matching prefixes until all answered or timeout.
Returns: a per-role digest. Children write everything to thread-keeper so you can also inspect via tasks()/dialog_search() afterward.
visible=False (default for tournaments — opening 5 Terminal windows is
obnoxious). Override per-need.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| roles | No | skeptic,generator,critic | |
| cwd | No | ||
| timeout_s | No | ||
| visible | No | ||
| model | No | ||
| effort | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |