# Cooks

- **Event:** [The Agentic Evolution Hackathon](https://cerebralvalley.ai/e/mongo-db-london-hackathon)
- **When:** Sat, May 2 at 9:00 AM – 9:00 PM (GMT+1)
- **Where:** CodeNode, London, United Kingdom
- **Placement:** Finalist
- **Team:** [Kazybek Khairulla](https://cerebralvalley.ai/u/Kazybekkh), [Dheer Maheshwari](https://cerebralvalley.ai/u/dheerm), [Tharit MH Khan](https://cerebralvalley.ai/u/Idea), [Reece Rodrigues](https://cerebralvalley.ai/u/XreeceX)
- **GitHub:** https://github.com/Kazybekkh/LiveRecall
- **Demo video:** https://www.youtube.com/watch?v=pN9iCj97ncQ
- **Gallery:** https://cerebralvalley.ai/e/mongo-db-london-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongo-db-london-hackathon/hackathon/gallery/22

LiveRecall is hands-free clinical decision support for the bedside: a clinician points/asks a camera (phone or Ray-Ban Meta glasses) an unfamiliar medical equipment, asks a question, and gets a grounded answer with the authoritative text, thumbnail, and citation in seconds. LiveRecall ingests a multimodal catalog (text + image + vector embedding per apparatus) into MongoDB Atlas, uses Atlas Vector Search for semantic retrieval, and drives a multi-agent pipeline (vision → routing → retrieval → reranking → answer) coordinated via change streams-MongoDB as both the knowledge base and the agent bus. Decision support, not diagnosis-the clinician stays in the loop.

---

Markdown version of https://cerebralvalley.ai/e/mongo-db-london-hackathon/hackathon/gallery/22. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt