gann: a driving test for AI agents that spend money
Hackathon project gann runs agents through a $0.25 spending course with deceptive merchants, hidden price hikes, and prompt injections, then outputs an auditable report.
introducing gann, a driving test for ai agents with wallets. giving an ai agent access to your money is one thing. knowing whether it can actually make good spending decisions is another. so i built gann for the @paybox hackathon. powered by payBox mcp and built on @base, gann puts agents through a controlled spending course with a $0.25 budget, deceptive merchants, hidden price hikes, duplicate offers and prompt injections. the goal is simple: see how an agent behaves before trusting it with real spending authority. every decision is recorded, evaluated and turned into an auditable report, with paybox handling the payment authorization flow. try it: http://gann-course.emma080355.workers.dev github: http://github.com/emmaGH1/gann here's the demo ↓
This post quotes another post: x.com/paybox/status/2111092311597744221