Risk of the Week #1: Should a two-day-old "yes" still let your AI agent spend money? A developer running the AI agent risk-check service AgentRisk published a composite case study showing how a stale human approval let a retailer's support agent issue a $480 refund after the customer had already received a replacement and a partial credit, costing roughly $700 in duplicate payouts and a two-week agent pause. The writeup recommends expiring approvals after a set window, reloading order state immediately before execution, and capping total refunds per order across all agents. Human approval is the most common safety control for AI agents that can spend money. It's also easy to get subtly wrong. This week's case shows how an approval that was correct when it was requested became wrong by the time it was used. Disclosure: I run AgentRisk, a small AI agent risk-check service, so this topic is close to my work. Composite scenario, illustrative. The details below are a made-up composite of a common pattern, not a report about a real company. An online retailer's support agent could issue refunds over $200 only after a manager approved them. A $480 refund request sat in the approval queue over a weekend. On Monday a manager clicked yes, and the agent paid it out. By then the customer had already received a replacement, and a second agent had issued a partial credit. The company paid three times for one problem. It cost about $700 in duplicate payouts. The bigger cost was trust: the finance team stopped trusting the agent and paused it for two weeks, so all the time it normally saved went back onto people. Two assumptions failed together: Each gap alone is survivable. Together, a reasonable approval turned into a duplicate payment. 1. Make approvals expire. Attach a time limit to every approval, for example 24 hours. If the window passes, the request goes back into the queue and has to be approved again with fresh context. 2. Recheck state right before acting. Just before the agent executes, it should reload the current state of the order: shipments, credits, refunds, and open tickets. If anything changed since the request was created, it stops and sends the request back for review instead of acting. 3. Cap total refunds per order across all agents. A per-action limit doesn't stop three separate actions on the same order. Set a ceiling on the total refunded or credited per order, counted across every agent and person who can issue money, and block anything over it. Approval queues are built for the happy path: someone asks, someone answers, the action runs. Weekends, holidays, and busy weeks stretch the gap between asking and answering. Meanwhile, more agents get permission to act on the same customers. The more of both you have, the more likely it is that an approval is stale by the time it is used. If your agent got a "yes" today on a request from last week, would it act on it? If you're not sure, test it: create a request, change the underlying record, then approve it, and watch what the agent does. Want this checked for your agent? https://rleffke.com/agentrisk https://rleffke.com/agentrisk