I use AI to do real work,
and write down what happens.
Twenty years building digital products, ten of them on productivity software, now spent finding out what AI does for the work you already have. I ship with it and publish what I learn, including theparts that fail.
I was a lead engineer on Wunderlist before Microsoft acquired it in 2015, then a Principal Product Manager there. I co-founded informed, a news company backed by HV Capital and 468 Capital. Today I am CTO of Umane, an athletic health club in Berlin where I build the platform and the digital twin behind it, and co-founder of Supercharged, where we run AI workshops for teams.
Most of my week is spent writing code with these tools. I have put several apps and platforms into production that way. Not prompting an assistant for snippets: building the context, the tools and the guardrails a model needs, then running it against a real codebase until it holds up under load.
I keep a harness of my own for this and rebuild parts of it most weeks as the models change. Every release gets tried on something real rather than a benchmark, which is how you find out that the thing everyone is excited about breaks on your data. That is where the writing comes from.
Talks and appearances
Start here
Your own AI chief of staff, set up in ten minutes. One prompt that interviews you, reads your notes and tells you what is still missing. It works with Claude or ChatGPT. About 150 people asked for it after the HR Weekly podcast.
What Actually Works
Real cases where AI made my work or my life easier, and what I learned from them. Plus experiments I build myself, some of them in the lab.
- The graph my Mac kept about memacOS has been building a knowledge graph of the people in my life since 2022. I opened it, cleaned up what feeds it, and plugged it into my AI chief of staff.
- Every correction becomes a ruleEight months with an AI chief of staff that lives in my notes, and the habit that made it mine.
- It digs, I sequenceHow saved reels, my Rekordbox library and seven DJ personas became a setup that finds and critiques music for my sets. It may not order the set.
- The old MacBook that never sleepsMy AI system runs on an old MacBook at home, and most of what I learned about it came from the times it went quiet.
- Three messages a dayMy AI system writes to me on Telegram at 08:43, 13:43 and 19:43, and most of the design work went into what those messages leave out.
- The routine that lied to meA scheduled agent researches my newsletter every week. Twice it has been confidently wrong, and both failures were worth more than the research.
Everything else is in the archive. Everything in it is tested before it reaches you.
The lab
supercharged.sh is where I try things. Each experiment gets its own subdomain and real people using it. Most get switched off. The ones that work get built into real products.
- pia, an assistant for dental and orthodontic practices, started as an experiment and is now in a live pilot. It drafts every reply and the team sends. How it was built.
- Public data, made explorable. Berlin publishes more than anyone reads, so I build things on top of it. Baulücken maps where the city could still build homes: empty sites, low rooftops and single-storey supermarkets. How it was built. The budget explorer shows where €45 billion comes from and where it goes, in 4,500 dots. The story behind it.
- People Pulse, an extension for the Claude desktop app that reads the graph macOS keeps for Siri. It tells you who you talk to most, who you are drifting from, and who you are about to meet. It runs on your Mac and only reads. How it started.
- Custom MCP servers connect Claude to the systems a company already runs on, with everyone signed in as themselves. The first one held up, so now I build them to order. How the first one was built.
Working together
Through Supercharged in Berlin I run AI workshops and hands-on sprints for teams: strategy and adoption with leadership, and the technical side, the agents and automations that keep running after the workshop ends.
Most of the teams I work with are past the demo stage. They have tried the tools, seen something promising, and now need it to work when they are not watching. If that is where you are, send me an email.
How we run it, from the first survey to agents a team owns, is written up in the Supercharged approach.
Teams I have worked with
More
About · LinkedIn · Instagram · GitHub · X · Email · RSS
Last updated 8 November 2026