Radar
Quick thoughts, observations, and things I recommend.
Claude Code is changing how I build
Been using Claude Code for a week now and it's genuinely changing my workflow. The agentic loop + file editing combo means I can describe architecture-level changes and watch them materialize. Not perfect, but the iteration speed is wild.
·
AITools
RAG evaluation is still an unsolved problem
Every team I talk to is building RAG. Almost none of them have good evaluation. We default to vibes-based testing — "does this answer look right?" — and call it done. The gap between building RAG and knowing if it works is massive.
·
RAGEngineering