Senior Product Designer for AI and data-heavy products.

I design complex products where trust can’t be assumed. Across GovTech, fintech, and enterprise SaaS, I’ve helped teams turn dense workflows, uncertain data, and AI-powered outputs into interfaces people can inspect, correct, and use with confidence.

13+ years on the craft

HCI & Interaction Design

Behavioural Design

English C1

Profile Picture 2

Built to work with global teams

DeliveringforUSandinternationalteamsfromBrazil4+yearsembeddedinglobalteamsacrossLATAM,theAmericas,andEurope·Markerr(NewYork)·Capstone(BTGGroup)·Nortal·Santander·
DeliveringforUSandinternationalteamsfromBrazil4+yearsembeddedinglobalteamsacrossLATAM,theAmericas,andEurope·Markerr(NewYork)·Capstone(BTGGroup)·Nortal·Santander·
DeliveringforUSandinternationalteamsfromBrazil4+yearsembeddedinglobalteamsacrossLATAM,theAmericas,andEurope·Markerr(NewYork)·Capstone(BTGGroup)·Nortal·Santander·

Trust is my specialty,
so here's the evidence first:

Led the UX of an AI-powered audit platform — redesigning the workflows behind the writing of audit instructions and reports, in one of the country's most skeptical institutions.

30

faster audit reporting e-TCE

30

faster audit reporting e-TCE

30

faster audit reporting e-TCE

My work on Data Studio and Ask Markerr helped Markerr grow from data provider into product company — a repositioning that ended in its acquisition.

2

revenue growth, ending in acquisition

2

revenue growth, ending in acquisition

2

revenue growth, ending in acquisition

Streaming responses, confidence indicators, partial results, graceful failure states, and a Generative UI system where agents assemble the interface at runtime. All in production.

Ask Markerr – LLM patterns, shipped — not theorized.

Ask Markerr – LLM patterns, shipped — not theorized.

Ask Markerr – LLM patterns, shipped — not theorized.

Selected Work

Every project shows its proof up front — a measured outcome or an honest label, before you click.

Every project shows its proof up front — a measured outcome or an honest label, before you click.

About me

About me

Ive spent my career in domains where getting the interface wrong isnt inconvenient its costly. GovTech, fintech, enterprise SaaS. That taught me to design for people who cant afford to trust blindly: find where the system breaks down before the interface, and fix it there.

Design has never been a solo act for me. The thinking is the teams and the ownership is shared but when something breaks, I carry it until its solved.

Blurry black-and-white figure in cap, white shirt, and black trousers.

How I work

Designing complex systems taught me a repeatable craft: understand the system, map the trade-offs, and turn ambiguity into an interface people can act on. Since 2017 I’ve applied it to the hardest case — non-deterministic, AI-powered products — but the method works anywhere complexity meets a human.

Designing complex systems taught me a repeatable craft: understand the system, map the trade-offs, and turn ambiguity into an interface people can act on. Since 2017 I’ve applied it to the hardest case — non-deterministic, AI-powered products — but the method works anywhere complexity meets a human.

Translate complexity into direction

Dense workflows, expert users, data-heavy screens: I start with the system, not the screen. Flows, diagrams, and information architecture that give teams a shared picture — then an interface that makes the complexity feel obvious.

Design the failure states, not just the happy path

Any system fails sometimes; non-deterministic ones guarantee it. The craft lives in what happens then: confidence cues, partial results, override paths, and audit trails — so people can rely on the output without trusting it blindly.

Coded Prototypes that follow design system specs

Use AI agent-assisted coding to ship working prototypes that follow design system specs. I built an internal AI wireframing tool with Claude Code, and TaleWeaver is my live testbed for agentic, stateful UX. Design decisions survive the handoff because they're already in code.

Coded Prototypes that follow design system specs

Use AI agent-assisted coding to ship working prototypes that follow design system specs. I built an internal AI wireframing tool with Claude Code, and TaleWeaver is my live testbed for agentic, stateful UX. Design decisions survive the handoff because they're already in code.

I can help you with

I can help you with

AI & Trust UX
Complex & Data-Heavy UX
Product Discovery & Problem Framing
End-to-End Product Design (UX + UI)
Prototyping Close to the Code
Design Systems
Conversational & Agentic Interfaces
UX Research & Behavioral Design
AI & Trust UX
Complex & Data-Heavy UX
Product Discovery & Problem Framing
Interaction Design
Prototyping Close to the Code
Design Systems
Conversational & Agentic Interfaces
UX Research & Behavioral Design

Off the clock, I go looking for focus in other forms:

be it a presence at kendo practice, freedom on a motorcycle, patience behind a black & white film camera the kind of photography where you slow down and earn the shot. And there's always a new hobby on the bench. Lately it's a story-driven RPG I'm building with AI, because I never quite learned to stop making things.

Off the clock, I go looking for focus in other forms:

be it a presence at kendo practice, freedom on a motorcycle, patience behind a black & white film camera the kind of photography where you slow down and earn the shot. And there's always a new hobby on the bench. Lately it's a story-driven RPG I'm building with AI, because I never quite learned to stop making things.

Off the clock, I go looking for focus in other forms:

be it a presence at kendo practice, freedom on a motorcycle, patience behind a black & white film camera the kind of photography where you slow down and earn the shot. And there's always a new hobby on the bench. Lately it's a story-driven RPG I'm building with AI, because I never quite learned to stop making things.

Daniel Canabrava Torres

dnltrs.com

Copyright © 2025 Umeh Chinonso. All rights reserved.