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.
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.
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.
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.