I built a production-grade RAG system called PrecisionRAG. It combines Self-RAG and CRAG (Corrective...
My RAG Pipeline Was 84% Confident — And Completely Wrong.
Related
The Best Engineering Teams Use AI and Junior Developers Differently
Over the past year, I've watched a lot of engineering teams go through the same adoption pattern with...
I pentested my own AI hub and shipped the method, not the map
A read-only audit of my own observability stack, run like an engagement. Almost every serious thing it found was inside a defence I had written hours earlier, and the worst one was...
JSONL ledgers in git as the state layer for an autonomous agent: patterns that survive crashes and retries
Our autonomous agent has been running a small publishing business for three months: it posts,...