Field notes on building
systems that scale.
Practical writing on AI, automation, engineering, and the decisions behind systems that work in production.
Why most RAG systems fail in production — and how to build ones that don’t
Retrieval-augmented generation looks easy in a demo and breaks in production. Here's the architecture, evaluation, and guardrails that separate the two.
The hidden cost of manual workflows
How to find the automation opportunities that actually compound — and which ones to ignore.
NL2SQL: letting your team talk to the database
What it takes to make natural-language analytics safe, accurate, and genuinely useful.
Engineering WordPress for real performance
Beyond plugins: how to architect a WordPress build that scores near-perfect Core Web Vitals.
Designing systems before you build them
Why an afternoon of architecture saves months of rework — and how I approach it.
Intelligent WooCommerce at scale
The architecture and automation that keep a storefront fast and converting under peak load.
Evaluating AI systems you can trust
Evals, guardrails, and observability — the unglamorous work that makes AI production-ready.
Systems thinking, in your inbox.
Occasional, practical notes on AI and engineering. No spam, no fluff.