The author reflects on their two-year experience using AI for coding, revealing that while AI can handle simple tasks, it struggles with complex, evolving projects. After encountering significant issues with the quality of AI-generated code, they decide to return to hand coding, finding it more effective and reliable.

After two months of coding with Claude Code, the author experiences a frustrating slowdown when reviewing pull requests and troubleshooting issues, despite initially enjoying the speed boost. The reliance on the AI for coding tasks has become a double-edged sword, as the author must still serve as a quality assurance engineer, often correcting errors and enforcing code quality. Skepticism remains about the future capabilities of AI in automating complex integration testing.