SPECIALTYFeedback-driven and user-oriented: I talk to users, ship early, iterate fast, and build what they'll actually use
01 TUNEBOX
My first startup in my first year of university.
Tunebox: the first startup I launched and the one that started it all. It was the most hands-on project I’d done before, and the thing that first lit the drive to build startups.
We entered the startup competition Start Academy and placed 2nd out of 120 startups.
Start Academy 2nd of 120VLAJO NextGen Fest Finalist
We were unsuccessful in finding product-market fit and decided on discontinuing the project, but it confirmed my ambitions to pursue startups 100%.
02 PLUG AND PLAY
Trained an AI model on a proprietary dataset of 800+ records
During my time at Plug and Play I ran first-pass review on 800+ pitch decks. I reviewed each one and kept the verdicts in a structured spreadsheet. This process was very repetitive, and as I looked at my growing dataset I thought: I can train an AI model on this data.
THE MODEL
83%Same invest-or-pass call as me, on meetings it never saw
85%Picks the deck I backed over one I passed (ROC AUC 0.85, against 0.75 for adding up the star ratings)
-40%Time I spent reviewing decks
It’s a gradient-boosted model, tested with grouped, nested cross-validation so no meeting leaks into its own test, and exported to ONNX so it runs inside the app.
NetZero takes a Python repository, finds the functions that do the most work, and rewrites them to use less energy. It started at HackEurope in Stockholm, a trip a few friends and I flew out for together.
Each function gets tests first, then three rewrites. A rewrite is only kept if it passes the tests, gives the same answers as the original on recorded calls, and measurably cuts the energy of every call.
An open-source TypeScript library built on TypeSafe’s Jev. You ask a question in plain English, like “does this email need a reply today?”, and Jev answers it for every new email, invite or message your users connect. Your code runs on the answer.
The events are typed from your own questions, so a typo is a compile error, and every action starts in dry-run. It works with Gmail, Google Calendar, Slack and Twitch today, and you can try it on a live Twitch chat in your browser.
After watching a video on double pendulums, I became obsessed with the visual output and wanted to try it out myself. I couldn’t find a website that had implemented a realtime simulation so I built one. Since the launch, the website has received over 1000+ unique visitors.
I’m moving to New York City to go all in on startups. I just finished my Bachelor’s in Computer Science, and I have decided I want to continue my learning in a different way.
From the moment I learned what a startup even was, I haven’t been able to look away. There’s a switch in my brain I can’t turn off, that gets me excited when I find a new idea I can work on, or build something that someone mentions has been annoying them.
So why move to NYC? The startup scene in Belgium is growing, but it just doesn’t compare to what’s available here. People here work harder, move faster, and have a completely different mindset: one I resonate with much more. I wanted to learn from more experienced people here, so that’s what I’m doing.
I want to join a growing team with a LOT of ambition. Almost everything I know, I learned by building. So that’s what I want to keep doing: build a lot, build fast, and build big.
