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.
RAG explained by building it: the smallest working app with Spring AI
You don't need LangChain or a vector database to understand RAG. The whole loop fits in two Java classes — and building it that small is the point.
Keep readingAutomate invoicing with MCP: my Invoice Ninja server
“Log 45 minutes of weekly meeting on the Audioempire project, cost 0.” One sentence, done. Behind it sits an MCP server I run myself — and one day where it deleted tracked hours.
Keep readingClaude Code Subagents & Skills: The Practical Guide
An agent that does everything does nothing well. Subagents and skills are the difference between a toy and a tool — here you build both, from a real example, and learn when each abstraction is the right one.
Keep readingMCP Enterprise Adoption: Outgrowing the Tinkering Phase
97 million SDK downloads, enterprise auth in the standard — MCP has outgrown the laptop. What that means for teams moving from prototype to production, and the five questions to answer before the first production server.
Keep reading1M Token Context: Feed Your Agent Like an Architect
Sonnet 5 reads a million tokens. Most people still feed their agent one file at a time — and give away the actual leap. What big context changes in practice, where it hurts, and a rule of thumb for daily work.
Keep readingAI Agent Governance for SMBs: What August 2 Actually Changes
August 2 is in every compliance newsletter — and just before the deadline, Brussels postponed the high-risk rules to late 2027. So it's all moot? Exactly wrong. What actually applies to SMBs running AI agents, and the one-page governance minimum.
Keep readingRescue 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.