Code Review

Making AI reviews useful in pull requests

by

AI code review becomes noisy quickly on busy pull requests. These are the patterns I would use for managed comments, finding identity, severity, evidence and merge gates.

The Real Value of GitHub Copilot Rubber Duck

by

GitHub Copilot Rubber Duck is interesting not because it adds more AI to the workflow, but because it focuses on a more important problem. In agent-driven coding, the real issue is often not generating code, but catching weak assumptions and flawed plans before they spread across larger changes. This post looks at why a second opinion inside GitHub Copilot CLI makes sense, where it could genuinely help, and why review quality matters more than more generation.