Building Fiuto
In the last few months I independently built and designed Fiuto.ai, an end-to-end AI user research automation tool. To design and build it solo I had to rely heavily on agentic workflows, which I designed to replicate the way a real product team works, from discovery to design to delivery.
Open fiuto.ai ↗ Full design automation presentation ↗ Start with part 01 →
The /ux family on a surface that already exists. One orchestrator and five skills in a single session: it grounds itself in the current stories, ranks what needs fixing, puts variants up for me to pick, translates the pick into components and checks what was built against it.
01Parts 01 to 02
Core flows in automated design
Redesigning surfaces that already exist: first a batch of simple admin components, then a complex panel with states and variants, both inside the coding agent and without a Figma handoff.
- 01 30 Jun 2026 Batch-updating simple components in an automated redesign A batch of admin atoms redesigned inside the coding agent, from review to Ladle stories, with no Figma handoff.
- 02 30 Jun 2026 Redesigning complex components A review, states, translation and fidelity loop on an implemented share panel.
One feature from question to production. The card on the board is remade at every step: grounded in research, narrowed to a direction, drawn as components, planned in phases, checked on staging, then live. The three marks on the track are the points where I decide.
02Parts 03 to 06
A new feature from design to delivery
One feature followed end to end: grounded from scratch, handed off as real components, planned and built in verified phases, then released to production.
- 03 1 Jul 2026 Designing new features with AI Grounding a new feature in product data and a fixed visual baseline before implementation.
- 04 1 Jul 2026 From an approved design to real components One approved mockup into real components, a verified render and a spec a fresh session can build from.
- 05 1 Jul 2026 Planning and building a feature with the build agent A locked design handoff becomes researched decisions, approved phases and verified implementation.
- 06 1 Jul 2026 Releasing the feature to production Surveying the release batch, proving migrations, checking staging and promoting to production.
Where a direction comes from. Four weekly scans feed one synthesis, and the synthesis reopens a roadmap decision: an option is struck out, the rest are ranked or parked. The two lanes on the right are the work that follows.
03Parts 07 to 09
Using research in automated design workflows
Where the direction comes from: a weekly competitive read that reopens a roadmap decision, the delivery that follows one of its findings, and the prototype a whole journey needs before it can be judged.
- 07 3 Jul 2026 Automated research for product direction and feature delivery Turning a competitive finding into a planning decision without treating the agent's report as a verdict.
- 08 3 Jul 2026 From a research project to a delivered feature How a research outcome moves through plan, design and QA checks, implementation and post-build review.
- 09 3 Jul 2026 Prototyping a whole user journey A text-heavy plan becomes a clickable journey, then a fidelity-checked build contract.
A QA pass run by agents. The orchestrator fans one build out to ten browsers, each driven by its own agent collecting passes and failures. What comes back is a single report: what held, what broke, and the defects ranked with the layer each belongs to.
04Parts 10 to 12
Reviewing and improving implemented experiences
What happens once the code lands: an implemented flow walked against the design it came from, the visual touches that give the product its tone, and a QA review run by agents in real browsers.
- 10 6 Jul 2026 Refining a feature after implementation Comparing an implemented journey with its approved design and routing each fix by scope.
- 11 6 Jul 2026 Adding visual touches to working screens Placing an animation on a screen that already works, without turning it into a design project.
- 12 15 Jul 2026 Visual QA with a swarm of agents Choosing between a browser review swarm, synthetic-user testing and a planned QA ticket.
Contact
Get in touch
Product design lead across research, design systems and handover, with coding agents in the loop. Contract, outside IR35, or a permanent lead role.
- Available
- Now
- Location
- London, remote or hybrid, UK and EU
- Right to work
- UK settled status, EU citizen
- RolesLead Product Designer, Principal Product Designer, Design Engineer
- ScopeResearch, design systems, prototyping, handover, QA with agents
- Email[email protected]
- LinkedInlinkedin.com/in/dariocodipietro