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. Built with Swift. Visual style inspired by classic Atari arcade art and EC Comics.
This project is inspired by pirate radio, video signal intrusions, and the strange hours of early cable—when broadcasts felt like discoveries rather than content. A continuous feed of archival footage, experimental films, and forgotten transmissions. Tune in to the livestream on the web, YouTube, Twitch, or Kick.
Price History Companion helps consumers take control of purchasing decisions by tracking actual price history across major retailers. Instead of relying on retailer "sale" claims or algorithmic pricing manipulation, users build their own intelligence about what products really cost over time. The system compares current prices against historical averages to reveal when a "deal" is genuine versus artificially created. This is especially valuable for people with chronic conditions who need specific products regularly—giving them the confidence to buy strategically rather than reactively based on marketing perception.
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.)
Phase I of conversational classifiers: a system of seven specialized agents that analyze user utterances across different layers of complexity—from granular behavioral signals to deep narrative patterns and motivational drivers.
Each agent operates independently to detect specific signals in user language, creating a rich composite understanding that can inform conversational flow, support appropriate pacing, and recognize moments of growth, risk, or insight.
This notebook builds on Phase I by taking the multi-bot analysis output and demonstrating how a chatbot might construct a supportive, human-like response. The response is not diagnostic—it integrates core elements commonly used in therapeutic conversation: empathy, validation, and reframing.
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. Build your personal heroic saga with themes of resilience and growth, inspired by Joseph Campbell's Hero's Journey.
Best Buy's AI-Assisted Self-Diagnosis is a concept-to-release microsite embedded in BestBuy.com that helps customers self-assess hardware and software issues using Geek Squad's twenty-five years of call transcripts and troubleshooting models. The application demonstrates three distinct AI facets: Conversational Design for natural interactions, Machine Learning for diagnostic pattern recognition, and Automated Handling for resolution workflows.
Originally designed for laptop triage, the system's success led to expansion across all Best Buy service areas, demonstrating scalable conversational design and production-quality execution for a Fortune 100 retailer.
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.
