I turn ambiguous ideas into AI products people can use, inspect, and trust.

Graded Chinese listening from real news, with synced pinyin and translation. Web, iOS, and podcasts.

• I shipped the learning loop, so stories, audio, and vocabulary all match each learner's HSK level.
• Episode production runs as an agent workflow I codified: an LLM reviewer strips out the English and reads each script's Chinese on its own, flagging lines no native speaker would say, and vocabulary is checked against the level before any audio is made.

An AI coach for amateur athletes. It reads their training data and writes plans they can understand and change. Chinese beta.

• I own the agent — tools over activity data, a coach that proposes and revises plans — and built the evaluation harness that caught it inventing workouts and features it lacked, fixed by grounding every claim in evidence.
• I built most of the product it sits in — activity import, planning, teams, the workspace.

Let people and external agents create, iterate, and deploy applications through an interface they can trust.

• I took Atoms CLI from 0→1, giving coding agents a direct path to create, inspect, validate, and deploy applications; it shipped internally, with two internal tools running on it.
• I defined a full-stack data workspace so non-technical builders could inspect and update app data without SQL.
• The platform was charging users to repair its own agent's mistakes — 34% of bug-fix requests — so I made the case for tiered pricing.

A cross-platform timer that makes breaks harder to skip while keeping its rules transparent.

• I designed it for Windows, macOS, and Linux around transparent rules and explicit user control.
• Seven years on, it's multilingual, still maintained, and kept alive by contributors I've never met in person.

An AI-assisted paper-cutting tool that helps creators work with cultural symbolism, not shape alone.

• I designed a system that connects visual form with cultural meaning, then evaluated it in a 16-person study.
• We published it as a full paper at ACM CHI 2025, where I'm co-first author and co-presented the oral talk in Yokohama.

A computer-vision defect-detection system that learned from normal production samples and ran in real time on low-cost edge hardware.

• I co-led it, pairing normal-only anomaly detection with a dashboard I shaped by watching the factory floor.
• I optimized the vision pipeline for real-time inference on roughly $40 of hardware and deployed it across 20 loom stations, where operators clear defects and managers watch production status.