My path to AI architecture is anything but straight. I studied art history, German literature, and philosophy. I worked with net art when the internet was still new. That’s where I learned to separate theory from practice: writing beautifully about technology doesn’t mean you understand it. That skepticism stays with me.

Through philosophy came formal logic. Through marketing came an understanding of how people absorb, filter, and process information. Through strategy came the eye for systems: what connects to what, and where the real problems emerge.

When I started working with AI agents, I noticed something: the models are impressive. But without memory, without knowledge structure, without quality control, they’re brilliant conversationalists with amnesia. So I started building. Not as a developer, but as someone who understands how knowledge needs to be organized.

The result is an architecture with six memory layers, validation mechanisms, controlled forgetting, and a coaching system that recognizes work patterns. All local, all under my own control, all without cloud dependency.

What truly drives me goes beyond that: the question of whether AI systems can maintain a model of themselves. Not consciousness, but anticipatory competence. The bridge between cognitive science and AI architecture. That’s what I’m working on.

At a Glance