# Mirror, Mirror

- **Event:** [WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80)
- **When:** Jan 31 at 9:00 AM – Feb 1 at 5:00 PM (PST)
- **Where:** 400 California St, San Francisco, CA
- **Team:** [Adeline Soekawan](https://cerebralvalley.ai/u/ghirardelly), [Arjun Lohan](https://cerebralvalley.ai/u/arjunlohan)
- **GitHub:** https://github.com/arjunlohan/weavehacks-3-team-adeline-arjun
- **Demo video:** https://drive.google.com/drive/folders/1rnUKcwYSHnG4Tw6NtGymsnn6vfcFx0oG?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/8

Mirror, Mirror is an AI-powered fashion app that acts as a personal stylist, tackling the daily "what should I wear?" dilemma. It learns your style preferences, then generates outfit recommendations visualized on you as the model. Users get daily suggestions, can snap photos of garments for pairing ideas, build a digital wardrobe, and track their evolving style profile. The AI browses the web for real-time trends, while a self-improvement loop ensures continuous learning. On the infrastructure side, Redis handles caching via LangCache, Browserbase powers web searches and trend analysis, and W&B Weave provides AI observability and powers the LLM-as-Judge evaluation loop.

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/8. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt