Daniel Canabrava Torres portrait
  • 01 - Senior Product Designer
  • 02 - AI Trust Systems
  • 03 - Behavioural Design
  • 04 - Implementation-Aware UX

Senior Product Designer for AI systems people can verify, correct, and rely on.

I design the trust layer between people and systems they cannot fully predict: shipped government-scale ML workflows, strategic LLM prototypes, B2B platforms, and decision-heavy product systems.

Based in Brazil (UTC-3) · English C1 · Remote-first for teams across the Americas and Europe · Open to relocation with visa sponsorship

Senior Product Designer with 13+ years across AI-native, SaaS, fintech, real estate, and high-stakes product systems.

Trusted by teams shipping complex product systems

MarkerrIliaVinciCapgeminiSantanderTCUWalkrNortal
13+
Senior Product Designer

AI-native, SaaS, fintech, real estate, and high-stakes product systems

2017 -> LLM
AI trust through-line

Shipped ML audit platform, now strategic LLM and GenUI prototype work

Specs
Implementation-aware design

React, TypeScript, Storybook, prototypes, state logic, and handoff specs

How I reduce uncertainty

I use research, prototypes, and state-level interaction models to make product risk visible before teams commit heavy build cycles.

Product risk

Turn ambiguous AI and workflow bets into testable product behavior before teams overbuild.

Engineering clarity

Map states, errors, correction paths, component behavior, and handoff specs so implementation intent is clear.

Business leverage

Connect trust mechanics to adoption, cycle compression, partner demos, and operating-model clarity.

Selected work

Project
chapters

After the proof pair, these chapters show the range behind the focus: B2B systems, fintech MVPs, enterprise workflows, and high-stakes product decisions with explicit evidence boundaries.

Designing the Trust Layer for Brazil's First Government-Scale AI Audit Platform hero media
0104

Shipped · Gov-Tech · AIDesigning the Trust Layer for Brazil's First Government-Scale AI Audit Platform

ML · Interaction Design · Gov-Tech · Trust UX / Sole Product Designer / 2017

Status: ShippedRole: Sole Product DesignerDomain: Government AI / ML audit workflowProof: Input shaping, verifiable AI output, correction surfaces

Designed the trust layer for Brazil's first government-scale AI audit platform — structured ML inputs and verifiable correction surfaces that cut federal audit cycles by 64% and Audit Instruction writing time by 63%.

63% writing-time reduction, 64% audit-cycle compression

Shows shipped AI trust at institutional scale for skeptical expert users.

2017-2018 government-scale ML proof.

Read the case study
0204

LLM + GenUI PrototypeTurning a vague AI ambition into a trustworthy product system

AI / LLM Interfaces / Senior UX Designer / UX Engineer / 2025 - 4 Months

Status: Strategic PrototypeRole: Senior UX Designer / UX EngineerDomain: LLM + GenUI real estate decision supportProof: Echo-before-resolve, streaming states, correction patterns

Strategic prototype that replaced filter-heavy real-estate search with conversational AI + runtime GenUI. Built with explicit trust architecture for high-stakes decisions and demonstrated as part of Markerr's AI roadmap narrative.

Supported partner demos and AI product direction

Shows current AI/LLM interaction judgment for high-stakes decisions.

Not a shipped end-user product.

Read the case study
Two platforms, one product: B2B pensions for HR and brokers hero media
0304

B2B PlatformTwo platforms, one product: B2B pensions for HR and brokers

Financial services / pensions / Senior UX Designer / 2022

Status: ShippedRole: Senior UX DesignerDomain: B2B pensions platformProof: Two role-specific products on shared foundations

Shipped dual-platform B2B pension experience in three months: one surface for HR administration, one for broker deal velocity, both on shared foundations.

User-tested dual-platform shipped in three months

Shows research-led product architecture for complex B2B workflows.

Read the case study
Ditching Spreadsheets to Make Financial Plans People Can Actually Follow hero media
0404

Shipped · Fintech · MVPDitching Spreadsheets to Make Financial Plans People Can Actually Follow

Financial services / wealthtech / Solo UX Designer / 2019

Status: Client-Reported MetricsRole: Solo UX DesignerDomain: Fintech / financial planning MVPProof: 3-day design sprint, seven goal-oriented dashboards

Led a 3-day design sprint and MVP that replaced spreadsheet-driven financial planning with seven goal-oriented dashboards — cutting manual updates 40%, client confusion calls 30%, and specialist onboarding time in half.

40% fewer manual updates, 30% fewer confused client calls

Shows speed-to-MVP and product-risk reduction in a complex financial domain.

Metrics reported by Walkr post-launch.

Read the case study

Senior Product Designer for AI-powered product systems people need to understand, verify, correct, and rely on.

Based in Brazil (UTC-3) · English C1 · Remote-first for teams across the Americas and Europe · Open to relocation with visa sponsorship

Let's talk