How do you know when an AI agent actually finished a task vs just says it did?

Been thinking about this a lot lately. The more agents get used for real work instead of demos, the more I keep running into (and hearing about) the same issue: an agent completes a step, reports success, and the output is actually wrong or incomplete. You don't find out until later, and by then it's harder to trace back where things broke.

Feels like this is going to become a bigger problem as more B2B tools ship agents into actual workflows instead of just chat interfaces.

Curious how others here are handling it:

• Do you manually spot-check agent output, or trust it by default?

• Has anyone built their own verification step for this?

• Or is a certain error rate just the accepted cost of automation right now?

Would love to hear how other builders/founders are thinking about this — feels like a problem a lot of us are quietly dealing with but not talking about much.