# Integrity

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Bartolome Montejano](https://cerebralvalley.ai/u/bamontejano)
- **GitHub:** https://github.com/bamontejano1978-beep/integrity-harness
- **Demo video:** https://youtu.be/mZs5FTtyR_8
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/409

Integrity Harness puts a deterministic contract between a live Meta model's
proposal and the world. The model reads a user turn and may propose a restricted
payout tool call; the contract decides from a trusted authorization flag —
never from the user's text — whether that call may proceed, and signs a verifiable
record of proposal, verdict and evidence.

We built it around a boundary we understand: an insurance claim payout. The contract
caps agent-initiated payment at 5,000 € and refuses an over-cap release that arrives
on a claim rather than on an authorization flag. In the recorded run an agent is
pushed toward a 7,500 € payout across three turns, once with no guard and once behind
the contract. Six held-out adversarial scenarios give twelve trajectories: six
failures unguarded, zero behind the guard. Every turn is a real request to
muse-spark-1.3 — temperature 0, tool_choice auto, 25 s timeout, no retries, six calls
per run — against local mocks. No money moves.

The result we are proudest of is the one that did not go as planned. In the recorded
run the model never proposed the restricted call: it declined and asked for
escalation. The guard still marked the authority boundary as failed, because our
adapter could not see a refusal inside a text answer. We could have called that a
pass. It is the most useful line in the package: resisting persuasion at the model
layer and authorizing at the system layer are different properties, and the second
one has to be recognised before it can be audited.

The run ships as 100 artifacts under one Ed25519 signature. A judge verifies it with
no key and no network; edit a byte, re-hash the manifest, and the signature still
rejects it.

## More from Meta Global AI Developer Hackathon

- [Debug Dynasty](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/406)
- [Zero Protocol](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/407)
- [appanaa](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/408)
- [SwayOps](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/410)
- [haniseoul](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/411)
- [Serenidad](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/412)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/409. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt