# Fix-It Flow

- **Event:** [Gemini 3 Hackathon London](https://cerebralvalley.ai/e/gemini-3-hackathon-london)
- **When:** Sat, Dec 13 at 9:00 AM – 10:00 PM (UTC)
- **Where:** CodeNode, London, UK
- **Team:** [Stephen Canning](https://cerebralvalley.ai/u/stephencanning), [Lea Rattei](https://cerebralvalley.ai/u/learattei)
- **GitHub:** https://github.com/essexcanning/Fix-It-Flow
- **Demo video:** https://drive.google.com/file/d/1IyrehfDRdzYL-TRZtgmVXUlTWvzBOMXT/view?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/gemini-3-hackathon-london/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gemini-3-hackathon-london/hackathon/gallery/7

Fix-It Flow is a "Living User Manual." It addresses "Multi-Modelity" by creating a tight feedback loop between Gemini 3 Pro (Reasoning) and Nano Banana Pro (Rendering).

Users upload a photo of a broken  object. Gemini 3 analyzes the fault and formulates a repair plan. It then acts as a prompt engineer, feeding a structured visual prompt—along with the user's original photo as inlineData—into Nano Banana Pro.

The result is a generated 2K resolution diagram that preserves the user's exact device context but overlays precise, legible 3D arrows and text labels (e.g., "Unscrew Here") showing exactly what to do. It transforms static troubleshooting into a dynamic, visual guide, leveraging Nano Banana’s state-of-the-art text rendering to ensure instructions are readable and actionable.

---

Markdown version of https://cerebralvalley.ai/e/gemini-3-hackathon-london/hackathon/gallery/7. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt