Lead Product Designer, design, research and delivery, equipped with AI
I design at every level of fidelity and organise what surrounds the screen: research, methods, follow-up. With AI, day to day: syntheses, task tracking, production in Figma, prototyping.
Case studies
Tessan
Patient app rebuilt in 30 days, an AI assistant under regulatory constraints, a design system and a product management system an AI can query, in three months.
- Health
- Mobile app
- AI
RiskOS
AI-augmented fraud detection. A functional prototype exploring human/AI collaboration under time pressure.
- Finance
- AI
- Prototype
Toolkit
0-to-1 Product Design for a Construction Tech SaaS. From pitch deck to MVP.
- Construction
- SaaS
- Startup
“He transformed business requirements into perfectly adapted user journeys, ideal for a startup like ours.”
Dailymotion Partner
Redesigning the professional video management suite for tier-1 media partners (CBS, Bein Sports).
- Media
- B2B
- Platform
01 / 04
All projects
I design the journeys and I take charge of the product design practice: the team, research, methods, where design sits in delivery, the design system.
Read my backgroundHow the work is structured
- 01
Structure the product
Each PM’s subjects in one roadmap, and design ready before development needs it.
- 02
Design the experience
Journeys, states and micro-interactions, prototyped in React or in Figma with Claude Code.
- 03
Deliver for implementation
Specifications, components and lots sliced with the squad, ready for the sprints.
Resources
Getting started with Claude Code
A practical guide for designers who want to bring AI coding tools into their workflow, from first setup to a deployed interface.
Guide · 9 chapters
Claude Code and Figma MCP: designing and implementing without switching tools
For the past few months, I have been using Figma MCP to read my designs directly from Claude Code, generate components that match the design, and iterate in real time between the mockup and the codebase. The workflow compresses the design-to-integration cycle from days to hours. I design in Figma, then Claude Code reads the component specs, spacing, tokens and layout through MCP, and generates production-ready code that stays faithful to the original intent. The interesting part is not the speed. It is the quality of the feedback loop: when I see the result instantly, I make better design decisions because I can evaluate them in context, not in isolation.
Article · AI
Let's talk
To talk about a product to design, a design practice to set up or the use of AI in a team, write to me.