Claude

Warning: This text is 100% human written (mistakes and all) As I wrote a few days ago, I have been a heavy user of AI over the last months. I have spent a lot of time in Claude Code and the terminal (my natural habitat — it’s fun, that it makes a come back (after too many years spent in Powerpoint, Confluence and Jira) and I enjoy using it (mostly — the CC application has some warts, but that’s another story). ...

Warning: This text is 100% human written I’ve (re-)discovered Agentic AI last December through a LinkedIn post forwarded by Ann Harding. The post mentioned Daniel Miessler and his „Personal AI Infrastructure" (PAI) project. Let’s just say — something clicked. I spent days (and many nights) learning, being amazed, working, building, refining Claude Code and what it can do for me. Six months ago, I saw the downsides of AI as it is being used today (energy use, climate, intellectual property, ethics, politics, techbros, social, …) and didn’t really see any „real" value being produced. That has changed! Not the first part, but the second for sure. ...

A month ago, I wrote about my first three weeks with Claude Code. At that point, I had a few tools working: an email CLI, a Tana integration, some calendar automation. It felt like a lot. I just ran the numbers. It’s considerably more than I thought. The Numbers Here’s what Claude and I have built together since early December: Project Files Lines of Code Supertag CLI (Tana) 163 44,116 Tool for my Psychotherapist wife 63 21,331 Email Skill 46 10,523 Daily Briefing - 4,481 PII Anonymizer - 2,894 Calendar (ical) - 2,235 Tado Thermostat - 1,551 Other KAI Skills 294 total ~70,000 Total: roughly 135,000 lines of TypeScript. ...

Three weeks ago I started using Claude Code, Anthropic’s CLI tool that lets Claude work directly in your terminal. Shortly after, I discovered PAI - Personal AI Infrastructure, a framework by Daniel Miessler that turns Claude Code from a capable tool into something far more powerful. The core insight of PAI is deceptively simple: apply the Unix philosophy to AI. Small tools that do one thing well. Composable. Each tool you build makes the whole system more capable. Daniel built the meta-layer - the skill system, the delegation patterns, the constitutional principles that keep Claude focused and effective. I get to build on top of that foundation. ...