Rag
Context Engineering for Production Agentic Systems
Beyond prompt engineering lies context engineering — the systematic design of memory, state, retrieval contracts, and compression layers that turn brittle LLM workflows into reliable, observable, enterprise-grade agentic platforms.
The Boring Go Layer Between Your RAG Demo and Production
RAG demos live in notebooks. Production RAG lives in ingestion pipelines — and I keep choosing Go for the unglamorous middle.
Why Most Enterprise AI Agents Fail
What eye-tracking research reveals about how experts actually retrieve and synthesize knowledge — and why current RAG approaches often miss the mark.