# GemVibe

- **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:** [JUJIE YANG](https://cerebralvalley.ai/u/jacky), [Jieyu Yang](https://cerebralvalley.ai/u/Jess), [Shashi Jagtap](https://cerebralvalley.ai/u/ShashiJagtap)
- **GitHub:** https://github.com/Shashikant86/GemVibe
- **Demo video:** https://youtu.be/VH-qNzlU9C4
- **Gallery:** https://cerebralvalley.ai/e/gemini-3-hackathon-london/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gemini-3-hackathon-london/hackathon/gallery/41

A model-aware prompt optimizer for vibe coding workflows, combining DSPy and GEPA to turn rough prompts into reliable, model-specific outputs. Vibe coding tools let users build with natural language, but prompt quality breaks creative flow when outputs feel misaligned. Our system automatically evaluates, restructures, and optimizes prompts to align with each model's reasoning style, delivering more reliable outputs with fewer iterations so users stay focused on building.

---

Markdown version of https://cerebralvalley.ai/e/gemini-3-hackathon-london/hackathon/gallery/41. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt