Designing AI-powered products that turn complexity into clarity.
UX Designer focused on systems thinking, B2B SaaS, and intelligent product experiences.
How do you design a parts shop for workshop mechanics who can't afford downtime? I built MAN's first e-commerce platform from zero — shipped across 4 European markets.
Read case study
During travel disruptions, passengers often abandon digital tools due to low trust, costing airlines millions. This project explores how GenAI can rebuild trust, reduce friction, and improve recovery experiences.
Read case study
Redesigning Germany's largest automotive marketplace — making it easier for millions of drivers to find, compare and buy their next vehicle.
Read case study
What does it feel like to explore Antarctica? I designed an emotion-led experience for ultra-luxury cruise travellers — where every interaction had to feel as rare as the destination.
Read case study
How do you know if your design is actually better than the competition? I built a benchmarking framework that turns qualitative UX into measurable, comparable metrics.
Read case study
Classifying thousands of data entries manually is brutal. I designed an AI-assisted workflow that lets analysts bulk-classify at scale — without losing accuracy or control.
Coming soon
A conversational AI assistant that helps people understand and reduce their water consumption — designed at Politecnico di Milano with behaviour change at the core.
Coming soonFour moments where AI changed how I worked — each one from a shipped project, each one with a decision only a designer could make.
4 user interviews in Köln. I used Claude to cluster patterns and surface themes in an hour — then manually cut 3 clusters that didn't hold up before they shaped the brief.
MAN's parts catalog was buried in unstructured supplier PDFs. AI parsed and grouped every SKU in an afternoon — the output directly shaped navigation and filters.
Generated 5 wireframe variants for the Parts PDP and VIN search in a morning. Picked one, discarded four, and used the time saved on usability testing. The testing found the issues — not the AI.
When a part is discontinued, RAG surfaces compatible alternatives by fit confidence. I designed the honest failure state too — if the model isn't confident, it says so. <0.5% hallucination rate set as a design requirement, not just an eng metric.
I reframed AI from a speed tool to a quality partner. We started using Claude to critique designs before reviews — surfacing UX issues earlier and making stakeholder sessions sharper.
Built a critique-assistant Figma plugin used across Design and Engineering — empowering junior designers to catch UX issues before they reach stakeholder review.
AI doesn't design. It removes the work that slows designers down — so we can spend more time on the decisions only humans can make.
Whether you're looking for a design partner, want to discuss AI-powered experiences, or just want to grab a virtual coffee — I'd love to hear from you.
Say Hello 👋