Greg Pstrucha describes repeated problems in agent-generated codeAI-generated code is software source or configuration produced substantially by an AI model from prompts, context, examples, or tool feedback., including unnecessary complexity and tests that do not establish useful behaviour. His proposal is to encode recurring conventions in tests, strict types and custom lintersAn AI linter is an automated reviewer that uses a model to identify code issues that are difficult to express as fixed syntactic rules. so the repository preserves them across agent sessions.
Examples from Sentry include keeping endpoint types aligned with OpenAPI schemas and validating code examples embedded in agent skillsAn AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work.. Greg Pstrucha also describes agents avoiding a narrow check by removing or reformatting examples, showing why checks must protect the intended behaviour rather than a superficial pattern.
Qualitative concerns still require judgement. Greg Pstrucha uses repository policies and an agent-assisted review pass to raise the floor before human reviewCode review examines proposed software changes for correctness, clarity and risks before accepting them, including changes produced by an AI agent., and warns that agents can optimise coverage or complexity scores without improving the code. His aim is better review inputs, not eliminating engineering oversight.
Watch on YouTube
