The Control Loop — How I Get AI-Generated Code Checked That I Can’t Read Myself

Reading code in order to control it takes two things: the language and the time. In the DI² project, both are missing. The maintainer comes from database development and knows neither TypeScript nor the web development the application is built in. And even someone who knows the language no longer reads through the amount of … Read more

The Agent Measures Where I Click — Debugging Postgres, Docker and a Swapping Server with a Coding Agent

A bug gets reported the way it feels: the message does not appear, the page barely responds, a tab no longer loads after a restart. A user can only describe what the interface shows, and the interface is the end of a long chain. A coding agent with access to the database, the container runtime … Read more

An EU Region Is Not an EU Provider — Vercel, Supabase and the GDPR Third-Country Question

“We host in Frankfurt, so we’re GDPR-compliant.” The sentence comes up in almost every conversation about Vercel and Supabase, and it is half the answer to a question that has two halves. The region answers where the data lives. It does not answer whose law applies to the companies that process that data. This article … Read more

One VPS, Four Environments, No Cookie Banner — How I Host a Next.js App with Self-Hosted Keycloak

For most web applications, the cookie banner question comes up too late. The application is built, an analytics script is in, the login page comes from a cloud service, and suddenly the very first page view needs a consent dialog that nobody planned for. The DI² project turned the question around. GDPR without a cookie banner was … Read more

Two Agents, One Working Tree — What Broke When I Ran Parallel Claude Code Sessions in One Git Repository

A Claude Code session opens a Git repository with no pending changes, works for half an hour and commits whatever has changed at the end. Run alone, that is correct. As soon as a second session or a human works in the same repository, the very same routine can pull someone else’s work into the … Read more

Agentic Coding from a User’s Perspective — Experience: The Work Doesn’t Disappear, It Shifts

Since spring 2026, two projects have been taking shape with the same coding agent: an ETL generator on Next.js and PostgreSQL, and this blog. The agent does not complete lines, it works through assignments in the repository. This article collects my agentic coding experience from a user’s perspective. I build databases, ETL processes and the … Read more

Setting Up a Claude Code Project with a Development Workflow and Database — the Open Starter Kit Explained

An empty repo and Claude Code, Anthropic’s coding agent in the terminal — that’s all it takes to get going. And that is exactly the problem: the model writes code immediately, but by default nothing ensures that a specification exists first, that a review happens afterwards, or that the database schema deploys reproducibly. A Claude … Read more

Maximal Template Over Empty Repo — a Claude Code Setup That Prunes Itself via /init

Every new project starts with the same ritual: create an empty repo, then hunt down the folder structure, the conventions and the workflow files from the last project — and forget half of them. A Claude Code project template can invert that reflex: instead of starting with nothing and building up piece by piece, you … Read more

Skills vs. Rules in Claude Code — What Auto-Loads, What Loads on Demand, and the Context Cost

Inside a Claude Code project’s .claude/ folder, rules and skills sit side by side: Markdown files that look almost identical — and behave in exactly opposite ways. That contrast is what Claude Code skills vs rules comes down to: rules are fully in context at every session start; a skill costs next to nothing until someone invokes it. Get … Read more