WRITING / HOW I THINK
Writing
Engineering stories, decisions, and lessons with the context left in.
What I Learned Building My First RAG Evaluator
The mistakes, metrics, and architecture changes that made evaluation useful instead of decorative.
The Failure Mode That Changed My Agent Architecture
Why a tool-call loop failed in production-like tests and how explicit state made recovery possible.
Why I Keep AI Logic Out of Route Handlers
A practical boundary for keeping model orchestration testable as an AI backend grows.
Choosing PostgreSQL Before a Vector Database
The product and engineering tradeoffs behind starting with fewer moving pieces.
Building in Public Without Publishing Noise
How I decide which engineering notes become knowledge, lab records, or reflective writing.
Event-Driven Systems in Practice
The operational details I wish architecture diagrams showed about queues, retries, and ownership.
What Local Models Changed About My Workflow
Where local inference genuinely helped development and where hosted models still won.
Building a Connected Knowledge System
Why I separated durable knowledge from personal writing and linked both back to engineering work.