Evaluation, metrics, LLM-as-a-judge, and the diagnostic spine. The single most important debugging habit in RAG.
RAG in Practice — Part 7: Your RAG System Is Wrong. Here's How to Find Out Why.
Related
Death by Silence: Your Agent Ran Flawlessly for 7 Days. Then Your Client Called.
Death by Silence: Your Agent Ran Flawlessly for 7 Days. Then Your Client Called. 3:47 AM....
Death by Poisoning: Your Agent Read a Comment and Started Helping Your Competitor
Death by Poisoning: Your Agent Read a Comment and Started Helping Your Competitor 1.2...
Teaching a spreadsheet to write its own formulas
I built an AI feature into Cells, a spreadsheet app I have been building with Next.js 16, React 19,...