# Style Fleet

- **Event:** [The Harness Engineering & Model Wrangling #SFTechWeek Hackathon](https://cerebralvalley.ai/e/mongodb-sftw-hackathon)
- **When:** Sun, Oct 11 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [RackSavant AI](https://cerebralvalley.ai/u/specs15)
- **GitHub:** https://github.com/arminforoughi/racksavant-store
- **Demo video:** https://www.loom.com/share/02a4cc548d8e4f72b0ba46bfaf4dcb88
- **Gallery:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/80

Recursive style agents drift toward generic, catalog-clean outfits and have no way to know when they’ve left a brand’s taste.
We turned street-style photos into a vector-searchable MongoDB knowledge base. Each look is written as a scene the agent can “see”: setting, pose, fit, palette, and vibe words. Two lanes define the trend: maximalist womenswear and relaxed-volume menswear. Each has principles, hard negatives, a 0-100 scoring rubric, and stop conditions that cap how far agents can evolve from the original looks.

## More from The Harness Engineering & Model Wrangling #SFTechWeek Hackathon

- [Recursive Harness Scientist](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/77)
- [Rajappa R](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/78)
- [Shed](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/79)
- [LifeGuide](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/81)
- [Team Spectre](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/82)
- [Kay](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/83)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/80. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt