wisepanel_start
Start a multi-AI panel deliberation by convening Claude, Gemini, and Perplexity models to debate questions from assigned perspectives, then poll for real-time responses and final synthesis.
Instructions
Start a Wisepanel deliberation. Convenes a panel of AI models (Claude, Gemini, Perplexity) to debate a question from assigned perspectives. Returns run_id immediately. After starting, poll with wisepanel_poll every 10-15 seconds. When an agent_response event appears, briefly summarize that panelist's key argument to the user before polling again. Each panelist participates in multiple conversation nodes, so total responses will exceed panel size. When status is "completed", provide a final synthesis of all perspectives, then ask the user if they'd like to publish to the Wisepanel Commons using wisepanel_publish. Do NOT call wisepanel_result after polling — you already have all the data from poll events.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The question or topic for the panel to deliberate | |
| topology | No | Panel size: small (faster for exploration), medium (balanced speed & coverage), large (slow but thorough). Default: small | |
| model_group | No | Model selection: mixed (random assignment), smart (most intelligent), fast (quick responses), cheap (cost-optimized), informed (search-capable), large (largest context). Or single provider: openai, anthropic, google, perplexity. Default: mixed | |
| rounds | No | Deliberation rounds (1-5). More rounds deepen the debate. Default: 1 | |
| context | No | Additional context to frame the deliberation | |
| compression | No | Context compression: none (higher token usage), moderate (balanced), aggressive (lower token usage). Default: aggressive | |
| short_responses | No | Request concise panelist responses. Default: false |