Writing
Engineering write-ups, mostly about what breaks. I learn more from failure modes than from launches, and I write them down.
July 2026 · 8 min read
I built a self-correcting RAG pipeline. It scored worse than the baseline.
SHARP-RAG added a critic agent that verifies retrieved evidence before answering. Exact match dropped from 25% to 15% and latency tripled. The post-mortem taught me more than a positive result would have.