# embodiedCad

- **Event:** [Google I/O Hackathon](https://cerebralvalley.ai/e/google-io-hackathon)
- **When:** Sat, May 23 at 9:00 AM – 10:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Rajashekar V](https://cerebralvalley.ai/u/raj)
- **GitHub:** https://github.com/rajashekarcs2023/Google-io-2026
- **Demo video:** https://youtu.be/0e5L1Iht38g
- **Gallery:** https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery/128

EmbodiedCAD is a physical workflow compiler that turns a short video of a human performing a tabletop task into a robot automation blueprint. Using Gemini Robotics-ER-1.6 model for embodied scene understanding and Gemini 3.5 Flash Managed Agents for artifact generation, it extracts objects, zones, actions, and spatial relationships, then generates an Embodied Workflow IR, a CAD fixture/jig, a robot pick-and-place plan, a 3D simulation, and an automation report. Our demo shows how a simple human assembly task can become an editable robot workcell blueprint in minutes.

---

Markdown version of https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery/128. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt