# Vi

- **Event:** [Built with Opus 4.7: a Claude Code hackathon](https://cerebralvalley.ai/e/built-with-4-7-hackathon)
- **When:** Apr 21 at 12:00 PM – Apr 27 at 2:00 AM (EDT)
- **Where:** Online
- **Team:** [Gil Caspi](https://cerebralvalley.ai/u/gil-caspi)
- **GitHub:** https://github.com/gilcaspi/claude-maestro
- **Demo video:** https://youtu.be/JHhUD4aP9nQ?si=JZtLfpaiw3xdZWyb
- **Gallery:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/285

Claude Maestro - Team OS for Healthcare & Life-sciences AI Squads

Healthcare AI delivery teams reinvent the same scaffolding on every engagement — feature engineering, cohort building, compliance docs, monitoring. Maestro is a Team OS that ends that. It's built on Claude and the Vi Platform: 190M de-identified patient records (the Vi Data Web) plus a foundation model trained on that data (Vi-FM). Applied AI engineers, data scientists, compliance leads, and FDEs work portfolio-wide instead of one engagement at a time. Every skill an FDE writes — underwriting an ROI, drafting an HCC compliance memo, building a cohort — gets shared org-wide. Every engagement starts from the last one, not from zero. The compounding library, Vi-FM predictions, and shared agents (deep research, monitoring, drift detection) turn one-off project work into a delivery platform

---

Markdown version of https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/285. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt