Find the strongest case against your decision.
Challenge a decision or claim from both sides, surface hidden assumptions, and leave with a provisional brief.
How Counterpose works
Two AI roles argue opposing cases. A blind assessment then identifies the deciding issue, the assumptions in play, and the evidence that could change the result.
Make the proposition precise.
Add the context that should constrain both cases. Only material entered as evidence will be treated as supplied evidence.
Edit either assignment before the debate begins.
How the method works
Position assignment and speaking order can be randomized to reduce model-order effects. The assessment role sees anonymous sides, but it is only model-independent when you select a different underlying model. Its factual score measures evidence discipline within the supplied material, not external verification.
Free hosted debate — two rounds: 4 responses (two per side) and a single assessment. For more rounds and your own models, use BYOK.