# Fifty Eleven AI

- **Event:** [Built with Opus 4.7: a Claude Code hackathon](https://cerebralvalley.ai/e/built-with-4-7-hackathon)
- **When:** Apr 21 at 12:00 PM – Apr 27 at 2:00 AM (EDT)
- **Where:** Online
- **Team:** [Ian Walmsley](https://cerebralvalley.ai/u/packetloss404)
- **GitHub:** https://github.com/packetloss404/vellum
- **Demo video:** https://www.youtube.com/watch?v=tB2kS0MhOb0
- **Gallery:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/162

Solving complex problems and using the frontier models to long research tasks. Not just research or deep search but the ability for it to be done over time while the user is away. If new information is found while the agent is researching it follows it's path to help make its decision. Its not just deep research here is a 2 page paper, it's research over time and allowing new facts to be introduced while that same string of research is ongoing. I wanted to challenge how long I could make the model think.

---

Markdown version of https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/162. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt