Uploaded February 2026 | Updated September 2026, 1 week ago

---

Engineering workflows require translating logic into executable, physical solutions. Anupam Pathak, an R&D lead in Google’s Platforms and Devices division, tested Gemini 3 Deep Think to accelerate the design and prototyping of complex physical components.

Taking in text prompts and image references, Deep Think reasoned through geometric constraints, Deep Think reasoned through the geometric constraints required to generate a 3D-printable turbine blade design—a task that typically requires specialized CAD expertise.

Learn more at https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-deep-think

___

Subscribe to our channel youtube.com/@googledeepmind
Find us on X twitter.com/GoogleDeepMind
Follow us on Instagram instagram.com/googledeepmind
Add us on Linkedin linkedin.com/company/deepmind