Deep-dives on LLM-powered systems, agentic workflows, and production-grade web architecture from 18+ years in the field.
Loading articles...
A team tells me they are "moving to a multi-agent architecture," and I have learned to ask one question back: which one? The blank pause that follows is the act...
There are two ways to use Claude Code, and they produce wildly different results. The first way is to open it, type a request, read the suggestion, accept or re...
The conversations I have with leadership teams about AI all sound the same now. They have the budget, a Copilot license, an enterprise Claude contract, an inter...
There is a pattern I keep running into when I review applications that were built primarily with AI coding tools. The app works in the happy path. The demo is g...
Every AI coding assistant starts the same way: completely clueless about your project. You open Claude Code or Cursor, and the first thing you do is explain you...
I get asked some version of the same question every week: "How do I become an AI Engineer?" Sometimes it comes from a junior developer. More often, it comes fro...
Every RAG tutorial follows the same script. Load documents, split into chunks, embed them, store in a vector database, retrieve the top-k results, pass to an LL...
I have been using Claude Code daily for over a year now. Not as a novelty, not as an experiment — as a core part of how I ship software. The difference between ...
I wrote a practical guide to building MCP servers earlier this year. It covers the basics — setting up a project, defining tools, connecting to Claude Code. If ...
Every product launch in 2026 seems to include the phrase "AI agent." Customer support chatbot? Agent. Form that auto-fills fields? Agent. A wrapper around a sin...