The system
A daily multi-factor trading system. Scores US and NL stocks on 13 proven factors, decides when to enter, when to exit. Live with €10,000 of my own money from late June 2026.
Building a production system with AI, without writing a single line of code myself.
I'm doing this through a fully automated trading system that runs live with my own money. Follow all the architecture, decisions, mistakes, and learnings here. Two worlds in one experiment: the technical side of AI-driven development, and the financial side of systematic investing.
Why this, why now
Every idea I've had on the shelf for the past ten years, I'm now building with AI. Without the help of large software firms. What used to cost hundreds of thousands and require a full team, I now build myself.
This is the moment to tackle one of those old ideas at scale: a model-driven trading system that operates on the market without human intervention. Investing is my passion. AI-driven building is my exploration. This is where both come together.
My role: designing, reviewing, testing, deciding. I don't write code myself. All code is generated by AI, I steer where needed.
Latest updates
15 Jun 2026 · 3 min read
Post #36644 tests, and why it matters
At the end of a long working day the counter stood at 644 passing tests. A nice number to look at. But the number itself is not the point. The point is what those tests do on a day when I am tired, in a hurry, or overlook something.
Read more
12 Jun 2026 · 4 min read
Post #35Verify over assume
A change to the database returned the message "Success. No rows returned." Sounds good. The problem: nothing had actually changed. The message was true and misleading at the same time.
Read more
11 Jun 2026 · 3 min read
Post #34Three times infrastructure, twice a bug
In a single day, four things went wrong with my trading system. A failed morning run, two failed builds, and a bug that only showed itself when a sale went through. Four red flags.
Read more
What's coming
The technical journey
How do you build this as a non-programmer? Which AI tools actually work, which disappoint? I share everything: the stack, the prompts, the mistakes, the workarounds.
The learnings
Weekly updates on LinkedIn and on this site. Quarterly deep-dives. Mistakes are content, so are successes.
For whom
For you who's curious about AI-driven development: I show how to build a full production system with AI tools, from architecture to deployment. You'll get insight into choices where even software developers often take the wrong turn.
For you who's interested in systematic investing: I show how a multi-factor model behaves in the real world, not in a backtest. Transparent, with real money, through every high and low.
For you who finds both interesting: welcome, this is where it comes together.