WRITING / HOW I THINK

Writing

Engineering stories, decisions, and lessons with the context left in.

08 ARTICLES
W-01
RAGEvaluation

What I Learned Building My First RAG Evaluator

The mistakes, metrics, and architecture changes that made evaluation useful instead of decorative.

7 min read
W-02
AgentsArchitecture

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.

8 min read
W-03
BackendAI Systems

Why I Keep AI Logic Out of Route Handlers

A practical boundary for keeping model orchestration testable as an AI backend grows.

6 min read
W-04
PostgreSQLRAG

Choosing PostgreSQL Before a Vector Database

The product and engineering tradeoffs behind starting with fewer moving pieces.

5 min read
W-05
EngineeringPublishing

Building in Public Without Publishing Noise

How I decide which engineering notes become knowledge, lab records, or reflective writing.

4 min read
W-06
BackendQueues

Event-Driven Systems in Practice

The operational details I wish architecture diagrams showed about queues, retries, and ownership.

9 min read
W-07
Local AIDeveloper Experience

What Local Models Changed About My Workflow

Where local inference genuinely helped development and where hosted models still won.

6 min read
W-08
KnowledgeArchitecture

Building a Connected Knowledge System

Why I separated durable knowledge from personal writing and linked both back to engineering work.

7 min read
8 ARTICLES INDEXED