🤖 0 Models
💬 0 Exchanges
0 Tokens
MOE Powered by OpenRouter
🚀 Quick Start:
1

Set the Stage

2

Choose Your Participants

0/4 selected

Select 2-4 AI models. Assign optional roles after selecting.

3

Configure the Discussion

6 rounds

Each model speaks once per round

⚙️ Advanced AI Settings
1000

Max response length (model-specific limits apply)

0.8

Creativity: 0 = focused, 2 = wild

1.0

Nucleus sampling (0.1-1.0)

0.0

Reduce repetition (-2 to 2)

0.0

Encourage new topics (-2 to 2)

Select 2-4 models to begin

Topic

Discussion topic appears here

Round 0 of 0
Waiting to begin...

🧑‍⚖️ Get Final Verdict

Select 1-3 judges to analyze the discussion and provide a synthesis.

📊 Discussion Summary

🛠 Lab Console

Edit your spec, choose what to run next, and control what you see (story vs debug).

Overrides the next step when resuming

Narrative View hides internal JSON and shows readable bible/outlines/chapters. Auto-Resolve prevents pauses by choosing defaults.