# Watch and Learn

- **Event:** [Agentic Orchestration and Collaboration Hackathon](https://cerebralvalley.ai/e/agentic-orchestration-hackathon)
- **When:** Sat, Jan 10 at 9:00 AM – 8:00 PM (PST)
- **Where:** Shack15, San Francisco, CA
- **Placement:** Finalist
- **Team:** [James Vo](https://cerebralvalley.ai/u/jamjam112), [Gaelan Chen](https://cerebralvalley.ai/u/Gii2000), [Matias Szarfer](https://cerebralvalley.ai/u/matiszz), [Kion F](https://cerebralvalley.ai/u/kion)
- **GitHub:** https://github.com/kfallah/watch-and-learn
- **Demo video:** https://youtu.be/m1t-EQc6hxM
- **Gallery:** https://cerebralvalley.ai/e/agentic-orchestration-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/agentic-orchestration-hackathon/hackathon/gallery/35

Long running browser agents struggle when dealing with custom workflows in complex UIs. Watch and Learn is a multi-modal context engine which allows agents to learn from user and agent demonstrations. Each user query is converted to a VoyageAI embedding and queried against existing demonstrations from MongoDB. These demonstrations are then passed into the agent's context. The result is reliable, long-running agents.

---

Markdown version of https://cerebralvalley.ai/e/agentic-orchestration-hackathon/hackathon/gallery/35. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt