# tough

- **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:** [Om Kannan](https://cerebralvalley.ai/u/omythehomie)
- **GitHub:** https://github.com/hackathonmongodb/RSI_Harness.git
- **Demo video:** https://drive.google.com/file/d/1FeiDj8tRRQXlHbHlgqhBtRwMAZi5uHSv/view?usp=drive_link
- **Gallery:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/84

hx is a terminal coding agent that improves its own working environment from its own failures. Coding agents keep repeating the same mistakes across sessions, such as calling python on a machine that only has python3 or trying to run interactive programs without a terminal, because nothing about their environment changes after they recover. Putting every past incident into the prompt is not a fix either, since it bloats the context. When a real failure happens during normal work, hx reviews its own trace, finds the root cause, and decides whether to store a short general rule, file a specific case note, or store nothing. A new rule starts as a trial and is only promoted after it actually prevents the failure on a later task. Cases are loaded only when a quick relevance check says they apply, so the context stays small. A local web console makes all of this visible: you can watch each step of the agent loop live, see the exact prompt the model received, and read every rule and case it has written. In our tests with a deliberately weak model, real failures dropped from ten on the first task to one on later, different tasks, after the agent learned a single rule and promoted it.

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

- [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)
- [Airlock](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/85)
- [Preflight](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/86)
- [Agazayt](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/87)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/84. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt