# CtrlAltElite

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Patricia Y](https://cerebralvalley.ai/u/pumpkinpatch), [Sparsh Paliwal](https://cerebralvalley.ai/u/discoman123), [Yibo He](https://cerebralvalley.ai/u/Yibo)
- **GitHub:** https://github.com/Vercellent/attune
- **Demo video:** https://youtu.be/dA6VhZIuREo
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/17

Attune is an AI-powered experimentation lab for improving website flows. A business owner sets an optimization goal and captures a user journey; agents plan and build challenger page variants, assign real testers, record interactions and session replays, optionally track webcam gaze, and interview participants. The system scores each round, stores findings, and uses prior evidence to guide the next experiments. MongoDB stores labs, variants, sessions, recordings, findings, and versioned agent harness settings. Atlas vector search retrieves relevant findings and older digests. A bounded harness trial process evaluates changes to agent rules and experiment settings and can roll back regressions. The current demo uses a fictional Northstar procurement flow.

## More from The Harness Engineering & Model Wrangling Hackathon

- [AI Stylist and Smart Wardrobe](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/14)
- [Converge](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/15)
- [Levy](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/16)
- [Reflexes](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/18)
- [MongoHive](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/19)
- [Ada](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/20)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/17. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt