The Code Exorcist Pattern: Why AI Agents Should Diagnose Bugs But Never Write the Final Fix

Originally published on tamiz.pro. The promise of autonomous software engineering is seductive. The vision is simple: feed a production incident ticket to an LLM agent, and it writes, tests, and deploys the patch by morning. In reality, this fully automated loop is a recipe for subtle, costly regressions, security vulnerabilities, and a complete loss of developer intent. The "Code Exorcist Pattern" proposes a more mature architecture: AI agents act as senior diagnosticians who excavate the root cause of a bug, but they never touch the actual codebase.