Design thatships itself.
Research, product design, production code, and AI systems — one continuous practice. No handoff, no relay race, no gap between the idea and the live product.
12 live productsLondon · WorldwideAI · UCD · Design community · Tesla
Built end to end. Nothing outsourced.
12 live products spanning AI, user-centred design, and Tesla — all live, all shipped.
01 / 07
UCD & AI
Specialist assistants, publishing tools, job discovery, and operating systems for people who practise user-centred design.
01UCD Botsucdbots.comA collection of focused AI assistants for user-centred design work.Case study ↗↗ 02UCD Botucdbot.comA practical AI companion for everyday UCD questions and tasks.Case study ↗↗ 03UCDOps Agentucdagent.comAn evidence-led AI agent for the complete UCD pipeline.Case study ↗↗ 04UCD Jobsucdjobs.comA focused home for user-centred design opportunities.Case study ↗↗ 05UCD Coachucdcoach.comThe design industry decoded daily, with sources and signal.Case study ↗↗ 06UCD Chatucdchat.comFree AI chat for UX, research, and service design.Case study ↗↗ 07UCD Surfucdsurf.comA searchable archive of design intelligence.Case study ↗↗
02 / 02
For design community
Public design systems and evidence-based UX laws for interfaces that stay usable as they grow.
01DesignOps Worlddesignops.worldA global directory of design systems for DesignOps teams.Case study ↗↗ 02UX Principlesuxprinciples.designThirty evidence-based UX laws and seven principles for designing how people think.↗
03 / 03
Tesla
Independent tools that make Tesla research, ownership, inventory, and vehicle data easier to understand.
01teslawayteslaway.ioAn independent AI wayfinder for Tesla owners and buyers.Case study ↗↗ 02teslaway pre-ownedteslaway.worldPre-owned Tesla inventory with transparent specifications.Case study ↗↗ 03teslavinteslavin.vinA free Tesla VIN decoder and recall-checking route.Case study ↗↗
One practice. No handoffs. No excuses.
Evidence-led research, interaction design, engineering, and deployment — held together as one continuous job.
Evidence before pixels.
Every product here started with a real problem, not a moodboard. When I build AI features, the output has to be traceable back to something a human actually said or published — that constraint shapes the architecture, not just the copy.
Design and code are one job.
Not two jobs with a handoff in between. The interaction model, the design tokens, the component API, and the deployed front end are the same decision expressed four times. Doing them together is what makes shipping in days instead of quarters possible.
AI in the loop, human at the gate.
AI does the assembly. A person approves the result. Every agent I've built has explicit approval gates, because a system that can't be stopped is a system nobody trusts in production.
Ship it, then learn from it.
Every case study here is live — real traffic, real learning, not a portfolio piece. Nothing is a portfolio mockup.
Make the next thing matter. Then ship it.
For AI products, design systems, agent experiences, and ambitious zero-to-one work.
Start a conversation ↗