Writing
Essays and technical notes on LLM systems, data engineering, retrieval, agents, and evaluation.
- A Retrieval Eval That Survives Index Changes
Notes on building a small, fixed question set for a RAG system so it measures correctness instead of quietly agreeing with whatever the current index returns.
- Evidence-First LLM Systems
A working note on the question this site keeps returning to: what evidence should technical work leave behind, and how to design pipelines so the evidence is a byproduct, not a chore.