I'm Adrian Föhl.
I build to understand.
A project that changed my perspective.
My assistant kept recalling decisions I had already moved on from.
So I built memory-metabolism: a field guide and scanner for outdated, duplicate and unreachable knowledge. The first full scan found 64 issues in July.
Why more memory made the answers worseWhat changed
Three cleanup chats resolved the open findings. The scanner now checks the structure; whether a statement is still true needs a separate review.
A file's date tells me little about whether its contents are still true.
Two more experiments
Rebuilding my agent team
Research and critical review still worked without the fictional colleagues.
Testing the AI on this website
The answers sounded good. I wanted to know whether they were right.
What I'm learning.
On knowledge, trust and the things you only notice by trying.
Testing AI answers
I Let an AI Speak for Me. Then I Tested It Like a Product.
7 min read
Rethinking agents
The Plumbing Outlived the Org Chart
7 min read
Recovering knowledge
Where Knowledge Dies Before It Is Stored
5 min read
Beyond the code
Half Filipino, raised in Germany.
At 19 I left for Australia, later Singapore and Sydney. The curiosity from back then now shows up in smaller things: hands-free cooking with a HoloLens, and AI assistants that should remember earlier conversations.
My path in six chapters
We need an app
Everyone wanted mobile apps. Nobody knew why. At T-Systems, I learned the hardest part: getting teams to agree on the problem before touching the code.
AR will change everything
I built my master thesis on a HoloLens, a hands-free cooking assistant. Then I tried to sell AR to German boardrooms. The tech was early. Most meetings ended with polite scepticism. But I learned something more important: how to make people trust a future they can’t see yet.
Big names, small steps
At adesso, I consulted for companies like STIHL, moving through roles from consulting to project management to product ownership. I learned how large enterprises run technology projects. But AR never took off, and I realized I wanted to be closer to the next wave, not managing delivery for the current one.
Is this AI thing real?
At a Fraunhofer spin-off, I tried ChatGPT in early 2023 and knew this was different. I pitched the pivot the next week. Not everyone was convinced. But I went ahead anyway, started talking to city governments that were just beginning to explore AI, and built a new business area from there.
Now make it work.
Then came the real test: a regulated corporate group with over a thousand employees and multiple subsidiaries, each with its own management. No more experiments. Everything had to go through compliance, works councils, and real budgets.
What can agents actually do?
The question isn’t whether agents work. It’s which decisions you can trust them with. I run agents daily for my own work, and I’ve already torn down one setup I was proud of. I document what changes as they take on more responsibility, and which lessons may or may not transfer to organisations.
Let’s talk.
A question, a different perspective or an experiment of your own? I'd like to hear from you.
This website can adapt to you.
In a short conversation, the AI picks stories from my projects that fit your interests. It draws on my published writing.
What I want to find out
How much of my thinking survives when an AI summarises it for someone else?
I write the sources. The AI writes the answer. Whether what comes out still sounds like me is what I keep checking.
How I tested the answersBuilt for agents too
Other agents can read every article as plain text and ask this site a question over the A2A standard, with no person in the loop. Whether any of them find it without being told, I don't know yet.