Twelve agents, two data lakes, one rule: no slides — only things that survive contact with reality. Built Beekeeper to 7M frontline users and an exit. Now back building with AI.
FIND THE BIGGEST PROBLEM.
CREATE FROM ZERO.
MASTER IT. TAKE IT TO THE LIMIT.
MY WORKBENCH
Every system on this workbench has a story that didn't fit on the card — what I tried first, what broke, and the thing I only understood afterwards.
My mornings run without me. Twelve agents wake at 07:30, read my body, my money, my emails and my calendar, and leave one brief behind. Five subscriptions died so this could live — USD 3,720 a year, cancelled.
Ninety-seven accounts, five currencies and eleven years of accounting, moved off a $750/year subscription and into a database I own — reconciled to the cent.
A boardroom you can play. Scan the QR in the printed book, take one of three seats, and find out what your decisions cost you.
Fourteen years of training, sleep and heart rate in one place — answering questions no single app could. Not Garmin, not Strava, not TrainingPeaks, and no trainer.
One draft a week turns a calendar and a training load into a food plan, a shopping list and a set of recipes.
The house runs on its own schedule — light, climate, presence and energy — and has since 2023.
Telemetry in, a race plan out — segment by segment, with a number to hit on each one.
Log how the day went in one number, say why out loud, and let a coach find the pattern you can't see while you're living it.
A consumer AI coach that reads a person's pattern over weeks and answers the question they are actually asking.
Production data analysis for a Swiss biotech. Chemical engineering, back in use.
A GPX goes in, a map scored for risk comes out — every segment rated on how likely it is to hurt you.
I'm writing them as I go, one at a time.
If it hasn't run in production against my real life, it's an opinion.
AI is amazing. But you can't trust that what comes back is exactly what you asked for. No testing, no releasing.
The agents decide what I look at. I decide what I do. That line never moves.
Every system here writes to something I control. Subscriptions end. Companies pivot. Fourteen years of my own data doesn't.
I'm a chemical engineer who ended up building and leading a software company. Fourteen years of Beekeeper, from an idea to 7M frontline users and an exit. That's a long race — and a long race teaches you fast what actually works and what only sounded good in the meeting.
Now I'm on the other side of it. No company to run — on purpose. A bench full of systems I built for myself, a training plan I engineer like a product, and the time to work out what sustains this rather than what replaces it. This page is the honest log — including the parts that broke.
READ THE FULL STORY →Start with the assessment. One 45-minute conversation, a written report five working days later: the tools to switch on this month, the one process to fix first, and the hours a week it returns. Fixed price, CHF 990 — credited in full if we keep going.
Or a crazy vision you've always wanted to make real? Those are my favourite. If you're sitting on something everyone calls unsolvable and you'd rather build than buy, let's talk. I take on two or three at a time, hands on the keyboard, building next to your team — not writing a deck about what they should do.
Working sessions, not a slide deck about AI. We bring your real problem into the room, pull it apart, and rebuild it live. Your people walk out having built something — not having watched me build something.
Scaling to 7M frontline users. What the exit didn't change. And what happens when you build AI systems as an entrepreneur and operator. English, German or Spanish — whichever the room speaks.
Personal AI training for CEOs and board members: four to eight sessions built around your role, your decisions and your calendar. No group, no fixed date, no full day blocked out.
Just email me at cris@grossmann.ai. I read every one myself.
WÜRENLOS, SWITZERLAND