Neural Cascade

See What Your Brain Sees

Type any experience — a whiff of coffee, locking eyes with a stranger, stepping barefoot into wet grass — and watch the brain light up in response. Each region activates with an explanation of why it fires, inside a low-poly head you can rotate.

Each input goes through the Anthropic API and returns a structured response — brain regions, activation order, and explanations. The API isn't acting as a chatbot; it's returning structured data the front-end plays back.

Face tracking turns the head into a puppet that follows your movement, with wireframe hands that mirror yours. Experimental, for fun.

Anthropic API (Claude Sonnet) Custom GLSL Shaders Google Apps Script MediaPipe Next.js Three.js Vercel
AI’s Role

Live Prototype (password below)
Demo Video (no audio)
GitHub Repository

Vision Command 2027

Eye-Tracking Video Game

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
AI’s Role

Demo Video
GitHub Repository

The Other Room

The Version They Kept to Themselves

Each profile is built from primary sources and biography — mapping the formations that produced them, the gap between the person and the persona, and the psychology underneath both. Carl Jung called that gap the shadow.

These profiles let the shadow speak. Each one is psychological scaffolding — tone, vocabulary, self-awareness, the topics that open and the ones that close — assembled from the record. Future iterations will deepen the voice with documented cadence from each subject's own interviews and writing.

Bring a question, a current event, or just start somewhere. The responses come from the psychological model, not the public record.

Anthropic API (Opus, Sonnet, Haiku) Google Apps Script Vercel
AI’s Role

Live Prototype (password below)
Screenshot Gallery
GitHub Repository
Chatbot Guidelines (reference)

SIMCesim

A Hotel Simulation, Rebuilt to Teach

When I was in a Mini MBA program, one of the courses ran on Cesim Service, a business simulation app where teams compete by running a virtual hotel. The tool worked mechanically, but it taught poorly: decision fields without labels, value ranges, units, or definitions, and almost no explanation of the terms or the cause-and-effect behind them. My whole team finished the first session without actually learning anything.

SIMCesim is my rebuild of that interface — same structure, but with the missing learning layers added in: guided decision steps, plain-language field explanations, the reasoning behind each input, and in-context economic principles for people who've never studied business administration.

Anthropic API Inline SVG Tailwind Vercel
AI’s Role

Live Prototype
Final Presentation.pdf

Waypoints

Trip Planning by Interests

A private map of places I want to visit: history, architecture, landscapes, and the music I love—things like Edinburgh Castle, the Cliffs of Moher, or more tailored things like Salford Lads Club, where The Smiths shot a famous photo for their The Queen Is Dead album.

Adding a place takes just a snippet of text like “clkwork ornge tnnel”, link, or screenshot and identifies the rest with coordinates, title, description, photo, and rationale, then drafts the pin for me to save.

Also, an agent called Scout can be triggered to look for places I haven’t found yet. It learns what I care about from my pins, searches the web, checks each find against fixed rules, and gives me a shortlist to review.

Anthropic Claude API Claude Web Search GitHub API Leaflet OpenStreetMap Vercel Wikimedia Commons
AI’s Role

Live Prototype

Waypoints Poster Grid

Posters From My Travel Pins, Auto-Generated on a Swiss Grid

Turns the places saved in Waypoints into posters laid out on a strict Swiss typographic grid. The posters generate themselves: pin a place, and the pipeline writes the copy, scales the photos, sets the type, and decides where everything lands. It gives me a way to revisit the places I’ve pinned, and it continues to teach me how grid systems work: a grid lab changes margins, columns, gutters, baseline, and rows while a sample poster rearranges live.

One pipeline gathers facts about each pin: Wikipedia facts with sources, photos with free licenses, and colors pulled from those photos. A second has Claude write the copy from those facts only and place every element on grid cells. Code checks the layout, a Claude critic scores it in grid terms, and it retries until it scores 7 or higher.

Anthropic API GitHub Pages OpenStreetMap Nominatim Playwright Wikimedia Commons Wikipedia APIs
AI’s Role

Live Prototype

Price Intelligence Tracker

Historical Product Price Data for Chronic Conditions

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.

This matters most for people who buy the same items regularly — especially anyone managing a chronic condition. Once you can see a year of real prices, you stop guessing and start buying when prices are actually low.

Next up — training models to identify the patterns behind the pricing. Transparency into when discounts are real, when they're staged, and when the same product gets quietly marked up before being marked back down.

Chart.js ChatGPT Claude Claude for Chrome Cron Python PythonAnywhere Selenium SQLite VS Code vØ by Vercel
AI’s Role

Live Prototype
GitHub Repository

MyDailyEpic

Transform Daily Struggles into Heroic Tales

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
AI’s Role

Live Prototype
User Admin
GitHub Repository
Character Sheet Prototype
Character Sheet Repository

PixelForge + VectorBuild

Three browser-based creative tools. All client-side, built in vanilla JavaScript with no server, no dependencies, and no framework.

PixelForge is a Photoshop clone built on the Canvas API, with two agents. The editing agent takes a plain-language request and carries it out with PixelForge’s own tools, checking its work as it goes. Feature Quarry researches how people use Photoshop and other editors and suggests which features to add next.

VectorBuild draws vector graphs and tunes how they render through a simulated CRT vector display. That's the technology behind early Atari arcade games like Asteroids and Tempest, where a beam traced glowing lines directly across the screen instead of filling in a grid of pixels.

Shimmer Lab tunes light that drifts behind an object or along its edges. Speed, spread, reach and palette are live controls, the test elements respond as you move them, and the settings copy straight out.

Canvas API GitHub Pages lil-gui Three.js Vanilla JS
AI’s Role

PixelForge Prototype
VectorBuild Prototype
Shimmer Lab Prototype

WCAG Accessibility Evaluator

AI-Powered WCAG 2.1 & 2.2 Compliance Testing

An accessibility evaluator that covers all 86 WCAG 2.2 success criteria — across all four principles: perceivable, operable, understandable, robust. Most automated tools catch around 30% of issues, mostly contrast and alt text. This one is built to find the rest.

Submit a URL, a screenshot, or code. You get back the testing method for each criterion, who on the team owns the fix (design, development, or product), the specific steps to remediate, and how the issue actually affects users.

Anthropic API Claude Code Netlify React Tailwind CSS W3C Standards
AI’s Role

Live Prototype (password below)
GitHub Repository
WCAG 2.0/2.1 (Claude Code Skill)

UX Audit Lens

Design Evaluation Through Multiple UX Lenses

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 to specific principles from Nielsen's heuristics, WCAG, and cognitive load research.

Each finding tells you not just what needs attention, but which lens caught it.

The system uses retrieval-augmented generation (RAG) to ground its analysis in a curated UX knowledge base rather than relying on the model's general training.

Anthropic API React Tailwind VS Code
AI’s Role

Live Prototype (password below)
Nielsen's Heuristics (Claude Code Skill)
UI Refactor (Claude Code Skill)
GitHub Repository (private)

Phase I: Conversational
Signal Processing

ML Notebook Prototype —
Behavioral Pattern Detection

ML notebook prototype that analyzes a user's language for specific behavioral signals — emotional cues, cognitive distortions, resilience markers, and motivational patterns. Each signal is detected by a specialized classifier agent, turning open conversation into structured data the system can act on: how to pace the conversation, when to offer more support, when to acknowledge growth.

ChatGPT Deep Research Kaggle ML Notebooks
AI’s Role

Kaggle Notebook (logic only) (Kaggle login required)
GitHub Repository
Conversation Classifier Bots.pdf

Phase II: AI Response
Generation

Constructing Supportive,
Human-Like Replies

ML Notebook showing how those signals get used. Instead of responding to the surface of what someone said, the system assembles a reply from the underlying pattern — the emotional intensity, the coping style, where the person is in their story, what kind of resilience they're showing.

Each response combines four things: empathic reflection, validation, cognitive reframing, and forward guidance. The result is a CBT-aligned reply built from behavioral evidence rather than keywords.

ChatGPT Deep Research Kaggle ML Notebooks
AI’s Role

Kaggle Notebook (logic only) (Kaggle login required)
GitHub Repository
Conversation Classifier Bots.pdf

Conversational AI Test Bench

What the AI Sees, and a Way to Judge It

Most conversational AI behavior is decided in code nobody can see. The test bench opens it up: personas, scenarios, signals, and governance rules, all adjustable in one place, by anyone.

A live conversation runs against the real pipeline, and every reply arrives with its trace: what the model perceived, what it decided, and what it chose to say or hold back.

Anthropic API (Claude) Node.js Vercel
AI’s Role

AI Test Bench (password required)
Case Study: HealthBot (password required)

AI Evaluation Harness

Measuring What ‘Good’ Costs and Sounds Like

How do you know if an AI product is any good, and what you’re paying for it? This is a repeatable way to find out.

The evaluation tests the same 45 test messages and grades every reply against its scope and rulesets. It also records what each conversation cost in terms of tokens. Then the quality and cost can then be compared across different models.

Anthropic API (Claude) Node.js Vercel
AI’s Role

Evaluation Harness (password required)
Case Study: HealthBot (password required)

Best Buy AI-Assisted Triage

AI-Assisted Self-Diagnosis

A conversational triage system trained on 25 years of Geek Squad call transcripts to guide customers through hardware and software troubleshooting. Combined decision tree logic, machine learning classification, and natural language patterns to reduce support call volume.

Started with a laptop MVP and expanded to all Best Buy hardware and software. The approach became the foundation for Best Buy's current support diagnostic system.

Its next design challenge: balancing customer control with guided problem-solving, replacing linear FAQs with a dialogue that adapts to the terms the user says or understands.

AI’s Role

BestBuy.com Triage Site
Facets of AI.pdf
Customer Journey.pdf
Creating a Conversational System.pdf
Making Tech More Human.pdf

Vetavize AI

AI-Assisted Veterans Benefits App

An AI strategy for Vetavize, a benefits app for veterans navigating the VA claims process. The roadmap progressed from basic writing help toward systems that could evaluate claim quality and track outcomes — each phase designed to capture which suggestions correlated with successful claims.

That data would feed VASPER AI, a model trained on what actually works with VA reviewers rather than what sounds right.

AI’s Role

Website | Company Video | Prototype
AI Development Strategy.pdf

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.