Multi Agent Debate

Multi-Agent Debate

A structured debate protocol for AI coding agents. Two agents independently diagnose a problem, critique each other's work, and iterate toward consensus — producing better solutions than either agent alone.

The included implementation uses [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and [Codex CLI](https://github.com/openai/codex) as the two agents, but the protocol is framework-agnostic and can be adapted to any combination of AI coding assistants.

Why Debate?

A single AI agent can miss things. Two agents reviewing each other's work catch more bugs, surface edge cases, and build confidence in the final fix — the same way human code review works. The structured protocol ensures agents engage critically rather than rubber-stamping each other's proposals.

How It Works

1. Independent Diagnosis — Both agents independently investigate the problem, identify root causes, and propose fixes.
2. Cross-Review — Each agent critically reviews the other's work, identifying agreements, disagreements, and missed issues.
3. Iterative Revision — Agents revise their proposals based on critique, defending or updating their positions with evidence.
4. Consensus or Escalation — The loop continues until both agents agree (consensus) or max rounds are reached (you decide).
5. Implementation — The agreed-upon fix is implemented automatically.

All agent outputs are saved to a `.debate/` workspace for full auditability.

The Protocol

The debate follows a structured loop with clear prompt templates for each phase:

Phase	What Happens
Diagnose	Both agents independently read code and propose a root cause + fix
Review	Each agent critiques the other's proposal
Check	Facilitator checks if disagreements remain
Revise	Agents update proposals based on critique (or defend their position)
Loop	Repeat review → check → revise until consensus or max round