AI engineer, designer, researcher.
I build the systems organizations actually run on.
I'm Jan-David Stütz. I build the AI systems organizations actually run on — the agents, multi-agent workflows, and pipelines that do the work, and the interfaces that keep a person in control where judgment still matters. A PhD in user-centered and neuro-symbolic AI, plus nine years across a global corporation, a hidden champion, and a startup, sit underneath all of it.
The hard call on an AI project isn't which model to use. It's deciding where the machine acts alone and where a person decides — then defending that split on cost, adoption, and whether anyone still uses the thing six months in. Most projects fail there, not on the model. Drawing it well is the work I do; research is how I hold the standard.
At a glance
15+ projects
Agents, multi-agent systems, and interfaces
9+ years
Shipping applied AI products
1 owner
Strategy to production, end-to-end
Featured Projects
Selected case studies
Three recent projects, one from each shape of AI work I build.
Who I work with
How to start working together
01
I have a problem, not a solution
The diagnostic start. I study the workflow, talk to the people in it, and come back with a map of where automation pays, where humans stay, and what to build first.
02
I have a direction, need the right build
Scoped delivery when the target is defined and the path is not. One owner from first interview to production — architecture, agents, interfaces, and the joints between them, without a handoff chain.
03
I have a system, need it better
Iteration on something already live. Adoption is stuck, outcomes underperform, or the human-machine split needs rethinking. I evaluate, rebuild the weak joints, and measure again.
Send the problem you're still debating internally — where no one's sure what should run on its own.