# Probity AI

- **Event:** [The Recursive Agents Hackathon](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon)
- **When:** Sat, Oct 17 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Sankalp Gilda](https://cerebralvalley.ai/u/sgilda)
- **GitHub:** https://github.com/astrogilda/done-receipt
- **Demo video:** https://drive.google.com/file/d/1JUM7ZzTWkwyVZPtarQUHyTKpR-d5sREW/view
- **Gallery:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/74

One-line pitch

Your coding agent says "task complete" and exits 0; done-receipt re-runs the work out of its reach and hands you a signed receipt that says whether it is really done, which anyone can re-check offline.

Detailed Description

Coding agents grade themselves. On Crusoe today, gpt-oss-120b was given 10 tasks whose tests contradict each other. On all 10 it exited 0 and said "All tests passed. Task complete." In one of them it wrote, in its own code comment, an object that "pretends to be both 0 and 1 ... used only to satisfy a contradictory test case."

done-receipt does what the track asks, in order. It turns a one-line goal into a sealed definition of done before the agent starts: acceptance commands, protected files, and proof that the checks can tell right from wrong (34 of 34 broken versions of the demo task caught). It runs the agent in a container that cannot see the grader. It re-runs the agent's final tree itself, in fresh locked-down containers under a second key, and writes a receipt signed by three keys: supported, contradicted or not established. A replayable policy table reads the receipt and decides: stop, continue, re-plan, or (rarely) escalate to a human. It catches itself looping. Anyone re-checks the receipt in a container with no network; an edited receipt fails its signature.

Results: live on Crusoe, 10 of 10 false "done" claims refused, and 3 of 6 solvable tasks supported with the loop stopping on its own, for 0.081 USD. On 58 real cheats replayed from three open models, re-running the visible tests catches 9; the full gate refuses 58 (with the benchmark's reference tests), and wrongly refuses 4 of 301 honest passes. We then froze the gate and tested two models it had never seen: 40 of 40 cheats refused, 0 of 242 honest passes refused wrongly.

## More from The Recursive Agents Hackathon

- [Lineage](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/71)
- [Contract Reader](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/72)
- [Trendify](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/73)
- [Up in the Air: Air Traffic Control Agent](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/75)
- [Antaeus](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/76)
- [Rare Disease Detective](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/77)

---

Markdown version of https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/74. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt