Writing
Field notes
Practical notes on shipping production AI features, scaling systems, and getting real leverage out of AI-assisted development.
-
Choose Boring Technology on Purpose: The 0-to-1 Stack
At the start of a product, the goal is to find out if anyone wants it — not to build something impressive. That goal should pick your stack, and it argues for boring technology almost every time.
-
Rolling Out AI Coding Tools Without Wrecking Code Quality
Handing your team AI coding assistants without a plan is how you get a flood of plausible-looking pull requests nobody fully understands. Here's how to get the speed without the mess.
-
Why Your RAG System Returns Garbage (and Where to Actually Look)
When a retrieval-augmented system gives bad answers, almost everyone reaches for the prompt first. The prompt is almost never the problem. Here's the order to debug RAG in.
-
Build vs. Buy: A Decision Framework for Your First AI Feature
Most teams answer the build-vs-buy question backwards — by starting with the technology instead of the cost of being wrong. Here's the framework I use to decide what to build, what to buy, and what to skip.
-
2.9s to 300ms: A Systematic Approach to API Latency
How to cut a slow API's p95 latency by an order of magnitude — not by guessing, but by measuring where the time actually goes and fixing it in the right order.
-
Building an Autonomous Coding-Agent Fleet
What it actually takes to move from one AI coding assistant to a fleet of agents that ship real work — orchestration, isolation, and the verification layer most teams skip.