# Watch Once

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Neil Lu](https://cerebralvalley.ai/u/neillu)
- **GitHub:** https://github.com/nt-neil/watch-once-teach-human-and-robot
- **Demo video:** https://youtu.be/GrNEYtSGzJU
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1856

Watch Once, Teach Human and Robot turns one teaching video into two outputs: a step-by-step manual for people (every step cites its source frames) and a validated operation JSON for machines (object / action / target / pre / done per step, plus per-step evidence).

Problem: how-to videos teach humans, but every robotics or automation team re-watches and re-annotates them by hand, and nobody publishes where video models stop being reliable. We built an honest, reviewable bridge from "the video shows how" to "machine-readable steps", with the failure cases written down.

What it does: upload a video (up to 3 minutes / 100 MB). A frozen pipeline probes it, extracts frames at original resolution, asks Meta Muse Spark for timed steps, validates the JSON strictly, and renders a manual with frame thumbnails. Default setting is prompt v6 + original-resolution keyframes, with an optional 3-run majority vote. Outputs also export to LeRobot-style task/subtask annotation, a VLA instruction sequence, and planner steps (annotation layer only — never run on a real robot). The same pipeline is available as a local web UI (real Meta inference only, no mock, 5 UI languages), a CLI, and an MCP server for agents.

Measured, not claimed: on frozen held-out sets evaluated once, the default passes 4/7 (set 1) and 6/10 (set 2); videos with no procedure correctly return 0 steps. Known limits: similar adjacent steps get merged and voting cannot fix that; sub-second UI events are missed; visually similar assembly steps are confused. Iteration took 248 paid calls (~US$8.52), about US$9 and over 250 real runs in total.

## More from Meta Global AI Developer Hackathon

- [Doddy Samiaji](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1853)
- [Metapase](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1854)
- [Vespera Day Agent](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1855)
- [BrahmiVoice](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1857)
- [SEALED](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1858)
- [Matrix](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1859)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1856. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt