# MerryCo

- **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:** [Slava Zinevich](https://cerebralvalley.ai/u/Slavazin)
- **GitHub:** https://github.com/slavazin/munchhausen
- **Demo video:** https://drive.google.com/file/d/1pYR8GbENN0L_XHU35lnbsxeW3O5FkaaN/view?usp=drive_link
- **Gallery:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/39

Agentic learning with a frozen agent is difficult. Agents can't reliably extract signal (cause of errors), and world-drift (the outcomes change due to the world of input changing) make it difficult to rely on old memories. 
For that I present my custom agentic harness-learner. It works by accumulating errors from agents that finish a job (in this case financial analysis), categorizing them and clustering them to learn shape, and then, after some accumulation uses an external oracle (in this case a strong agent that knows facts of the world) to create the rules. 
The memory corpus then has every agent use an adaptive hook-latch mechanism (think attention) that allows relevant rules to input case be injected into the model. 
Each rule features a full lifecycle, so rules can change and be forgotten

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

- [RCFL](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/36)
- [CrashTest](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/37)
- [Pehovski](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/38)
- [AgentTab](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/40)
- [WiredFront](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/41)
- [Mavericks](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/42)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/39. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt