Writing
Articles.
I write about useful AI, software systems, and the choices behind them. If something here gives you an idea, tell me about it.
04 publishedAgent Evals Need Decisions, Not Essays: Building with Jev
I built a small Jev evaluator to see what changes when models return typed judgments and code owns the final pass, review, or fail decision.
Delivering AI models globally is a systems problem
Training gets attention. Reliable delivery is where architecture becomes real.
What scheduling algorithms teach us about serving LLMs
Fairness, throughput, and tail latency are old systems problems wearing new AI clothes.
AI-first does not mean AI everywhere
Start with the problem, simplify the system, and use AI only where it changes the outcome.