A Claude Code experiment with three debating agents
This approach uses three agents inside Claude Code instead of asking one model for one answer. The Visionary creates a new idea, the Destroyer looks for weak and flaws, and the combines the opposing views into a stronger option. The loop becomes more intense over several rounds, and later the roles switch so each side has to argue from the opposite position.
After every round, an internal verifier checks the claims, hidden , counter-evidence, bias, and blind spots. If the result scores below 8 out of 10, the loop runs again. The goal is to move beyond the average answer that a single LLM often gives and find ideas that appear when different viewpoints clash.
One example applied the method to finding a viral growth idea for a CLI tool.
Key points
- Three agents split the work into invention, criticism, and .
- An internal verifier checks each round for weak claims and missed evidence.
- The loop repeats when the score is below 8 out of 10.
- Role switching is used to reduce one-sided thinking.
- The method may improve output quality, but it does not show token or cost savings.