# Ajay Upadhyay

- **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:** [AJAY UPADHYAY](https://cerebralvalley.ai/u/57Ajay)
- **GitHub:** https://github.com/57Ajay/teachOnce
- **Demo video:** https://youtu.be/pElnxe50ADQ
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1458

Browser agents that ask a model what to do on every click are slow, expensive and unreliable at volume. On our test task, a computer-use agent needed 27 model calls, $0.30 and almost 7 minutes per row, and completed 7 rows out of 10.

Teach-Once flips that. You do the task once in your browser while narrating it. Muse Voice Transcribe, Muse Spark and Muse Wonder compile the recording into a deterministic, parameterized workflow (plus a standalone Playwright script), which runs over a CSV file in about a second per row with no model calls at all.

When the site changes and a step breaks, Muse Spark looks at the new page and works out what changed (moved, a different kind of control, split into parts, behind a Next button, removed, a popup in the way), and SAM 3.1 confirms exactly where the element is. The patch is verified, saved as a new workflow version, and reused by every later row, again with zero model calls. When a change can't be healed (blocked access, a new mandatory field the data doesn't have), the run stops and says why after one model call.

It is not tied to one site: teach_live.py records on any website. On Demoland Hire, a modern React recruiting app included in the repo, three tasks taught by hand (add a candidate; search and remove one; schedule an interview through a three-step wizard with radio cards, a date, a custom dropdown and a switch) each compiled once ($0.16-0.43) and ran every CSV row with zero model calls, 1-2 s per row. With the app's own redesign switched on mid-run (new look, cookie banner, renamed menu and buttons, a dropdown turned into radio cards), the interview task healed on one row and finished 8 of 8 rows: 6 heals, $0.076 in total.

Results on the demo portal: 50/50 rows through a mid-run redesign for about $0.04 in heals; 20 of 20 random redesigns recovered (two-page forms, custom dropdowns, removed fields, popups) at about $0.055 each; at 10,000 rows a day, roughly $0.30 once to compile versus about $3,000 a day for the agent.

## More from Meta Global AI Developer Hackathon

- [Semantic Release Auditor](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1455)
- [Sachitha Madhuranga](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1456)
- [Xinogi](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1457)
- [HocBong Hunter AI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1459)
- [Jinboost](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1460)
- [uptodate](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1461)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1458. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt