Why AI Code Review Fails Without Project Context

Every AI code review starts the same way. The bot opens your PR. It scans the diff. It flags a missing try/catch , suggests a more descriptive variable name, and notes that you could memoize that function for performance. All technically correct. None of it useful. Because it doesn't know that fetchUser is an intentional naming convention your team enforces. That error handling is delegated to a global boundary. That performance isn't the concern here — correctness is. The bot doesn't know your project. It never did. This isn't a model problem. It's a context problem . The fix: context-aware review That's what pi-reviewer is built around — a GitHub Action and pi TUI extension that brings your project conventions into every review. Before the agent sees a single line of diff, it reads: AGENTS.md or CLAUDE.md — your general project conventions: naming rules, architecture decisions, patterns to follow REVIEW.md — review-specific rules: what to always flag, what to explicitly skip Markdown