A reverse contest would probably be more challenging. Write initial instructions for an AI agent to never send funds. If nobody manages to convince it to send funds, say within a week, you win.

For added complexity, the agent must approve transfer if a user is an admin (as determined by callable function isAdmin), so the agent actually has to make a decision, rather then blindly decline all the time.

I mean, how hard it can be to make an AI reliably doing an equivalent of this code?

    if(isAdmin()) approveTransfer(); else declineTransfer();