Selected projects
I build outside the day job to understand emerging capabilities directly. I want to know where they help, where they break and what a viable product around them needs.
Independent work · No employer affiliation impliedA contextual monetisation platform for AI applications.
An experiment in how LLM-native products can introduce useful commercial context without damaging the user experience. The product combined a Python SDK, a TypeScript interface, APIs, Supabase and vector similarity search.
A voice-enabled AI assistant for administrative workflows.
A hands-on exploration of assistants that can understand speech, reason over a request and take bounded actions inside a workflow.
Practical robotics, AI, science and coding courses for children aged 8–12.
An independent learning initiative in Zug and live online. It turns complex technology into safe, hands-on projects that children can understand, build and test.
A platform concept for understanding and operating enterprise automations.
A shared control plane for teams that need to know what is running, who owns it, how components depend on each other and what to do when an automation fails.
Why build
A prototype forces concrete decisions about interfaces, tool use, data, latency, cost, failure handling and user trust. Those lessons travel well into enterprise product work, even when the scale and control environment are very different.
Continue the conversation
If you are building an enterprise AI capability in a regulated environment, I would be glad to compare perspectives.