Marcos Rezende | AI Experiments in UX and Product Design

AI GOVERNANCE · UX SYSTEMS

Reversion AI Framework

Reversion AI is a 6-step framework and practical planning canvas that makes reversibility a structural requirement in AI interactions. Every system action can be undone, audited, or redirected by the user, by design, at the interface layer.

VIEW FRAMEWORK

Reversion Canvas — Model-Based Prototyping planning card showing a Modular Refactor scenario with High Risk classification, tools including Cursor, Claude Code, and GitHub Actions

NLP · COMPUTER VISION · HEALTHCARE AI

RX Reader

RX Reader uses computer vision and medical language models to interpret handwritten prescriptions and surface reliable medication information to pharmacists in seconds. Unclear handwriting is the input. Clinical confidence is the output.

TRY IT NOW

RX Reader AI — mobile app decoding handwritten prescriptions using AI, featured in the WHO Digital Health Atlas

AI AGENT · NLP · BEHAVIORAL SIGNALS

Veltra (Signal Detection)

Veltra detects typing friction in real time (words per minute, idle time, backspaces, focus switches), and triggers proactive channel switching before abandonment happens. Behavioral signals, not explicit commands, drive the handoff logic.

VIEW DEMO

> `Veltra — behavioral signal detection system showing AI-powered channel switching logic across Voice Agent, Human Agent, Callback, and Keep Typing decision paths`

PROMPT ENGINEERING · GUARDRAILS

Shard Protocol

Shard Protocol applies pre-execution prompt fragmentation, constraint mapping, and logic path validation to enforce safe, verifiable AI behavior. The protocol enforces what most AI interfaces assume: that intent was correctly understood before the model acted.

VIEW CASE

Shard Protocol — preemptive AI output control system, Top 10 at Bolt World's Largest Hackathon Writing Challenge

CODE · COMPUTER VISION · LLM

UX Wise AI

UX Wise AI combines vision models and LLMs to analyze UI screenshots and surface what code review never catches: UX flaws, accessibility gaps, behavioral drift, cultural mismatches, and privacy red flags. A reasoning partner that reads interfaces the way a senior designer would, and ships the audit in seconds.

TRY IT NOW

AI AGENT · APPLESCRIPT · API · HARDWARE

Clippy AI

Clippy AI connects ChatGPT to a physical keyboard via AppleScript, triggered by a single keystroke, in a 3D-printed prototype. One of computing's most mocked interfaces, rebuilt with a real brain. A provocation about what ambient AI assistance feels like when it is always one gesture away.

VIEW CONCEPT

Clippy AI — ChatGPT-powered assistant running in a custom GPT interface alongside a 3D-printed physical Clippy prototype by Marcos Rezende

AI AGENT · COPILOT STUDIO · AZURE DEVOPS

Priosense AI

Priosense is a Copilot Studio agent that replaces bug prioritization debates with a structured decision. It evaluates every issue by business impact, urgency, and resolution effort, then connects directly to Azure DevOps triage. Grounded in production workflows.

CONFIDENTIAL

Priosense — Microsoft Copilot Studio agent for bug prioritization, showing structured prompts for problem classification, impact evaluation, time-to-resolution, and relevance by business goals

GENERATIVE AI · PROMPT ENGINEERING

Re:Branded by AI Prompts

Re:Branded stress-tests AI as a creative partner in brand work. Built from over 200 curated prompts exploring one identity across its full aesthetic range. The output proves what structured prompt engineering can do when applied with design discipline.

WATCH VIDEO

HCI · CONVERSATIONAL DESIGN · DEMO

SmartEats

SmartEats is a concept for the AI Pin that replaces voice-based allergen detection with visual detection. Color-coded icons identify food intolerances in real time, making lunchtime safer and more independent in noisy public spaces. A design exploration proving that inclusive AI interfaces require intentional constraints.

VIEW CONCEPT