# Switchproof

- **Event:** [The Agent Arena Hackathon](https://cerebralvalley.ai/e/vultr-the-agent-arena)
- **When:** Sep 26 at 9:00 AM – Sep 27 at 5:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Roshni K R](https://cerebralvalley.ai/u/roshnik9998)
- **GitHub:** https://github.com/roshni2020/Costguard-
- **Demo video:** https://youtu.be/GqKKRTpI4LE
- **Gallery:** https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/30

Bank payment migrations fail in public and expensive ways: TSB's 2018 migration cost about £81m in fines and compensation. SwitchProof is an AI test team for these migrations. A tester writes the payment rules in plain English. A coordinator agent on Vultr Serverless Inference (GLM-5.3) plans the work, and a generator agent (DeepSeek-v4.1-flash) writes ISO 8583 test cases. Nothing runs until the human approves every test. Approved tests, plus a 10,000-transaction replay of IBM's public synthetic TabFormer dataset, run in throwaway gVisor sandboxes on Vultr Kubernetes, in two isolated pools on separate VMs: agent-written tests and replay data never share a machine. When the new system misbehaves (in our demo a seeded bug charges customers twice), a triage agent designs its own follow-up tests to find the exact boundary, explains the root cause and the money at risk, and the human blocks or approves the release. A real run on Vultr: 10,022 tests in 42 sandboxes, 0 errors, defect found in 8.9 seconds, $0.04 of AI cost. An isolation probe inside a real sandbox shows rm -rf /, internet, cloud metadata and escape attempts all blocked. The payment switches are simulated and the defect is seeded; everything else runs live on Vultr.

## More from The Agent Arena Hackathon

- [ligis](https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/1)
- [Wesam](https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/2)
- [Nusa](https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/27)
- [Cerberus](https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/28)
- [Airlock](https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/29)
- [MJ](https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/31)

---

Markdown version of https://cerebralvalley.ai/e/vultr-the-agent-arena/hackathon/gallery/30. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt