# Path Quest

- **Event:** [The Persistent Context Sprint Hackathon | Live at MongoDB .Local Build Fest](https://cerebralvalley.ai/e/persistent-context-sprint-hackathon)
- **When:** Thu, Aug 13 at 12:30 – 8:00 PM (PDT)
- **Where:** Pier 48, San Francisco, CA
- **Team:** [Anhadh Sran](https://cerebralvalley.ai/u/anhadhsran3101)
- **GitHub:** https://github.com/anhadh3101/path-quest/
- **Demo video:** https://youtu.be/Usvivp_4iT8
- **Gallery:** https://cerebralvalley.ai/e/persistent-context-sprint-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/persistent-context-sprint-hackathon/hackathon/gallery/23

Agents make predictions on what they need to do in order to complete a task. I built a context layer where the steps taken by an agent are stored in MongoDB, to be fetched on the next run. Think using Opus once and getting the same performance/path to success using Sonnet.

---

Markdown version of https://cerebralvalley.ai/e/persistent-context-sprint-hackathon/hackathon/gallery/23. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt