Every time I help figure out why a computer system broke, I hit the same hole. The logs show exactly what the system did. Nobody wrote down what it was supposed to do. On October 13, American Express (Amex) published the Intent Intelligence Framework, a plan to plug that hole before AI helpers, called "agents," start shopping for people.
Before the agent buys anything, you set your rules and approve them. Amex gives that request an ID number and a digital receipt that shows whether anyone has changed it. Both stay attached to the purchase: when the payment gets approved, when you call customer service, and when you dispute the charge later.
Amex wants that record for a reason. When a customer says "I didn't mean to buy that," the law requires Amex to investigate. Amex says complaints about AI purchases haven't gone up yet. This is also still only a proposal for how systems could connect, and no store has signed on.
I don't know yet how written-down rules will hold up in a dispute. "White Nikes, size 9" can be checked. "Something I'd actually wear" can't. And a signed record of the clear rule might end up proving you got exactly what you asked for, which could make your complaint harder to win.
Create: You pick the store, the most you'll spend, what you want, any conditions, and how many purchases the agent can make.
Update: You change those rules.
Cancel: You call it off before the agent buys anything.
Expire: The permission ends after a set time.
Use: One purchase, or repeat buys, like reordering paper towels within a set price and size.
At checkout: The agent pays with a limited stand-in payment code, never your real card number.
Mismatch caught: You asked for Nikes, the agent tried to buy Adidas, and Amex can stop the payment.
Fraud angle: The record shows which agent was allowed to buy what, and when.
Not yet shown: Whether stores will use it, whether it works with other systems, and who pays when something goes wrong.
