Everything I have built.
Four projects have written case studies: what the problem was, what I built, what it proves, and what it does not. The rest are hackathon builds, experiments, and research spikes, listed with the stage they actually reached.
Four systems
Also built
Hackathon builds, experiments, and research spikes. Listed with the stage they actually reached — most of these are not products.
Rebuilt ACT's voice-debrief slice as clean, standalone code: describe a job by voice, get asked two sharp follow-up questions, receive a structured teachable card.
Ask your security cameras what happened instead of scrubbing hours of footage — a local, on-device voice agent over multi-camera video.
Scoped identity, approval, and audit for AI agents before they touch real APIs, CRMs, and internal tools.
Robot QA without a terminal: upload a mission log, replay it in simulation, detect collisions and path deviations, compare policy versions.
Probabilistic open-play simulation for football — sample plausible futures from tracking data instead of predicting one.
Turns a plain-English board idea into structured PCB requirements, a formal spec, and a validation report. Built with a team.
On-device repair guidance built for the Cactus × Google DeepMind × Y Combinator Gemma voice-agent hackathon.