Projects — deep dives, not an archive
RL Soccer AgentA tabular Q-learning agent that learns to play 2-a-side soccer in your browser — and the playable proof that RL is more subtle than the tutorials suggest.playable2026→Free-Throw Prediction from Motion Capture1st place, SPLxUTSPAN 2026 Data Challenge — predicting where a free throw lands (angle, depth, left/right) from 69 joints of motion-capture data.1st place2026→CoCivil — Land Development Due DiligenceWon Google Studio AI at Hack Canada 2026 — turns a plain-English query about an Ontario property into a complete planning submission package.winner2026→ML, From ScratchNo high-level wrappers: MLP, CNN, RNN, and Transformer architectures implemented from first principles — each with a live demo you can try.fundamentals2025→
More on GitHub
whisper-flowPersonal push-to-talk dictation for macOS↗AgentGateScans AI agents before deployment — sandboxes them, compares actual vs. declared behavior, returns an allow/block trust verdict↗probabilistic-pitcher-physicsProbabilistic pitcher physics modeling and validation from public Statcast data↗lankiAnki for LeetCode — evaluates your code and explanations to schedule spaced repetition↗