A gaze-controlled arcade game for macOS inspired by Atari's Missile Command. Players defend cities leveraging built-in macOS Accessibility — Eye Tracking or Head Pointer to aim, with Dwell Control or Facial Gestures to fire. Visual style inspired by classic Atari arcade art and EC Comics.
ChatGPT Claude GitHub Kling macOS Accessibility Features SpriteKit Swift Xcode
Retailers use algorithms to make every price look like a deal. "Was $25, now $22!" But was it ever really $25? TruePrice tracks actual price history so you know what products truly cost over time.
For people who buy specific items regularly—especially those managing chronic conditions—this turns guesswork into strategy. You see patterns retailers don't want you to see, and you buy when prices are genuinely low, not just marketed as low.
Machine learning models are also in development to uncover the patterns behind retailer pricing—seasonal cycles, promotional rhythms, and the algorithmic rationale corporations use to set prices across channels.
Chart.js ChatGPT Claude Claude for Chrome Cron Python PythonAnywhere Selenium SQLite vØ by Vercel VS Code
AI-powered prototype that recognizes skincare products in real time, classifies formulas by function, and aligns them with personal skin needs—bridging science, design, and everyday experience.
ChatGPT vØ by Vercel
A ground station receiving Low Rate Picture Transmission (LRPT) data from Russian polar-orbiting weather satellites as they pass overhead. Images show a continuous strip of Earth captured during each ~10 minute pass.
Current Satellites: Meteor-M N°2-3 (137.1 MHz) and Meteor-M N°2-4 (137.9 MHz). Typical coverage: 2-3 visible passes per day per satellite over Minneapolis-St. Paul area. (Built off of a previous project, creating an aircraft location receiver.)
Claude GitHub Gpredict Python Raspberry Pi RTL-SDR SatDump SQLite
An AI-powered project that takes the same 3D building data behind Google Maps and transforms it into something entirely different — a stylized, scrollable isometric map of downtown Atlanta. The renderer is built and capturing the city.
Next, a fine-tuned image model will convert those photorealistic tiles into illustrated styles, with the architecture designed so new visual treatments can be swapped in by simply retraining the model.
Claude Code GitHub Google Maps 3D Tiles API MagicaVoxel Three.js VoxCity
Developed machine learning notebook analyzing user language through specialized classifier agents detecting behavioral patterns from atomic emotional cues and cognitive distortions to resilience indicators and motivational drivers, transforming unstructured conversation into structured signals that inform pacing, support level, and growth recognition.
ChatGPT Deep Research Kaggle ML Notebooks
Built notebook demonstrating how multi-agent signal outputs synthesize into context-aware, CBT-aligned responses assembled from detected behavioral signals (emotional intensity, coping patterns, narrative phase, resilience markers) rather than surface input alone. Each reply integrates empathic reflection, validation, cognitive reframing, and forward guidance, illustrating how structured behavioral modeling shapes meaningful conversational AI.
ChatGPT Deep Research Kaggle ML Notebooks
MyDailyEpic transforms daily struggles into epic tales. Share a frustration — missed bus, work conflict, life challenge — and watch it reimagined through fantasy, sci-fi, or mythology.
Grounded in cognitive behavioral therapy, the experience uses narrative reframing to help users identify core values and build resilience — no clinical language required. Inspired by Joseph Campbell's Hero's Journey.
ChatGPT Deep Research GitHub React Tailwind CSS VS Code vØ by Vercel
A fully client-side image editor built on the Canvas API, featuring layers, blend modes, a filter panel, and core tools like brush, fill, lasso selection, and crop. No server required — everything runs in the browser with zero dependencies.
Built as a modular vanilla JavaScript application, it demonstrates how complex creative tools can be architected and shipped without frameworks, leveraging AI-assisted development to accelerate feature depth.
Canvas API GitHub Pages Vanilla JS
A comprehensive AI-powered accessibility evaluator that goes beyond automated checkers catching only contrast and alt text issues. While most tools identify 30% of problems, this evaluator covers all 86 WCAG 2.2 success criteria across the four core principles—Perceivable, Operable, Understandable, and Robust.
Submit URLs, screenshots, or code and receive professional-grade evaluations with step-by-step testing methods, role-specific responsibilities (Design/Development/Product), actionable remediation steps, and real user impact analysis.
Anthropic API Claude Code Netlify React Tailwind CSS W3C Standards
Most design reviews rely on gut feel or a single checklist. UX Audit Lens runs your interface through multiple UX frameworks at once — paste a URL, upload a screenshot, or drop in code — and returns findings tagged by evidence-based principles drawn from established UX research and standards.
Each finding tells you not just what needs attention, but which lens caught it.
This project uses retrieval-augmented generation (RAG) to reason from a well-proven corpus of UX knowledge rather than generic AI responses available to anyone.
Anthropic API React Tailwind VS Code
Built conversational triage system analyzing 25 years of Geek Squad call transcripts to guide customers through hardware and software troubleshooting. Combined decision tree logic with machine learning classification and natural language patterns to reduce support call volume.
The system demonstrated how structured diagnostic flows could scale across product categories—starting with laptop MVP, then expanding framework to all Best Buy hardware and software. This approach became the foundation for Best Buy's current support diagnostic system.
Explored conversational design patterns that balance customer control with guided problem-solving, testing how AI-assisted triage could replace linear FAQs with adaptive dialogue.
An AI strategy for Vetavize that started with simple grammar and formatting help, then progressed toward sophisticated quality evaluation and outcome tracking—each phase designed to capture how our suggestions affected actual VA claim results.
This framework turned the roadmap into a learning system where every interaction would help build VASPER AI, the model that gets smarter by understanding which approaches actually work with VA reviewers.
The projects above are recent AI experiments. My full portfolio covers 10+ years of UX strategy, product design, and research across healthcare, retail, enterprise, and Fortune 500 clients.
