# Load Path

- **Event:** [Agents in Context Toronto: a MongoDB Hackathon](https://cerebralvalley.ai/e/mongodb-toronto-hackathon)
- **When:** Sat, Nov 14 at 9:00 AM – 9:00 PM (EST)
- **Where:** Toronto, Canada
- **Team:** [Sagar Patel](https://cerebralvalley.ai/u/sagar_patel), [Arad Moharrer](https://cerebralvalley.ai/u/Arad)
- **GitHub:** https://github.com/isagar2757/load-path
- **Demo video:** https://youtu.be/biyXonvHfHE
- **Gallery:** https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/23

Load Path lets several AI agents plan and fund bridge repairs under a fixed budget, and makes every action auditable. Each tool call, by an agent or a person, passes one policy gate before it runs: role, spend limit, budget envelope, jurisdiction, approved plan, and a reason on rejections. The decision, actor and policy version are written to a SHA-256 hash-chained ledger in Atlas. A MILP picks treatments for 198 Ontario bridges within a 250M envelope. When an owner rejects a condition reading, only the work that depended on it is reverted, newest first, an inspection is requested and the plan is re-solved. Stop rolls back the whole session. Data: Ontario bridge conditions, Open Government Licence – Ontario.

## More from Agents in Context Toronto: a MongoDB Hackathon

- [Bedley](https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/20)
- [Continuum](https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/21)
- [WhatAboutage](https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/22)
- [CONTEXT RETAIL : The Governed Memory Platform for AI-Powered Retail Operations](https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/24)
- [suture](https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/25)
- [Yes_chef](https://cerebralvalley.ai/e/mongodb-toronto-hackathon/hackathon/gallery/26)

---

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