AGENTS.md

Lauren Tan, who leads the Grok Bot desktop app at SpaceXAI, shared her team's AI coding playbook at the AI Engineer conference: encode every correction as a lint rule instead of prose in agent docs, keep the codebase clean so AI does not copy bad patterns, ban error-prone APIs and 99% of comments, and have AI run and self-verify its own work with recordings. The team merged 11,000 PRs last month with roughly 0.5% reverted, and the app is faster than at launch.

A longtime Claude Code user has migrated his primary coding harness to the open-source Pi after accumulating frustrations. The post recounts Claude Code's shortcomings from a personal-experience angle and highlights Pi's lightweight, highly customizable design. The migration narrative offers some reference for tool selection but lacks systematic benchmarking.