gpt-4o-mini

Code Review Pipeline

hardMulti-Agent8 tests

A two-agent code review system. The first agent reviews code and identifies issues. The second agent fixes the code. The final output should be working code only — no commentary, no markdown.

Agent Prompts

Reviewer

Analyzes the code and identifies bugs, issues, or improvements needed.

Fixer

Takes the review feedback and outputs only the corrected code.