Notes from the workshop.
AI builds fast — here I write about making it hold and sell. Agents, MCP, clean code, and the business behind it.
Rescue an AI-Generated Codebase: The Field Guide
The rescue wave is here: AI-built apps that tip over after three months, and legacy systems nobody understands. How to take over such a codebase — triage, tests, agent rules — instead of burying it deeper.
Keep readingWhat Is an AI Model — and How Do Machines Learn?
An AI model doesn't know anything — it has compressed patterns from data into numbers. Understand that once, and you understand why AI hallucinates and how to work with it. Explained simply.
Keep readingAI Prompting Basics: The Patterns That Don't Expire
Most AI answers are mediocre because the prompt is. Instead of the hundredth trick list: the four patterns that don't age — and why a good prompt is a small specification.
Keep readingFrom developer to AI expert: which skills survive
The agents do the boring work better than I do. So I asked myself: what's left of me? The honest answer — which skills depreciate, and which you have to build now.
Keep readingWrite your first MCP server in 30 minutes
An MCP server isn't magic: a handful of functions, cleanly described. Here you build your first one and plug it into your coding agent.
Keep readingThe last 20% decide whether you have a product
Vibe-coding gets you to 80% in minutes. But the last 20% are the whole job — and that's exactly what an agent can't (yet) do alone.
Keep readingAI code without tech debt: your review has to change
When the agent writes 200 lines in 20 seconds, you can't read line by line anymore. Review has to move from reading to interrogating.
Keep readingAI code without tech debt — the checklist
Sign up: the checklist plus new posts on AI engineering. No spam, unsubscribe anytime.