# Second Shift

- **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:** [David Shatsky](https://cerebralvalley.ai/u/davidshatsky), [Andrew Shatsky](https://cerebralvalley.ai/u/Ashatsky)
- **GitHub:** https://github.com/uyqv/MongoDB-Hackathon
- **Demo video:** https://youtu.be/fyuLbvF8t50
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/30

Second Shift is a long-horizon NeuroAI harness that keeps an agent pursuing one research goal across context resets, crashes, and changing constraints: improve EEG classification of imagined hand versus foot movements.
It directly addresses three parts of Long Horizon Engineering:
- Sustained, coherent memory: MongoDB Atlas preserves goals, experiments, and measured results. Each decision rebuilds its context from that evidence. With 10,000 synthetic distractor notes, the evidence packet remained approximately 1,200 tokens.
- Persistent goal pursuit: The campaign survives worker failure, reuses completed experiments, and adapts when the electrode limit drops from 64 to 9. All eight recovery checks and five constraint checks passed.
- Learning from hard metrics: Claude selects experiments using prior numerical results. Code processes EEG and measures performance. Our selected configuration achieved 73.2% sealed test balanced accuracy across five participants and 75 test trials.
We demonstrated these mechanisms on a small, real EEG research campaign. Billions of tokens and weeks of continuous operation remain scaling targets, not measured results.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Recall Gate](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/27)
- [Sudo Squad](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/28)
- [emirates](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/29)
- [Self-Taught Trainer](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/31)
- [Crucible](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/32)
- [LILI](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/33)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/30. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt