Skip to content

Can I see which actions an AI agent has run?

Short answer

Yes, and you should be able to. If a vendor won’t show you, that’s reason enough to rule them out. Every action the agent takes has to be logged with what it did, on which account, when and in which conversation. Without that log you can’t review a mistake, you can’t answer a customer who complains, and you won’t pass a mid-sized customer’s security questionnaire.

By Adrià Castany, updated

In detail

What has to be logged

The action, the account, the time, the conversation it came from and the data it checked before acting. With those five you can rebuild any case. Without the last one you know what happened but not why, and why is what you need to fix it.

What it’s used for

More for improving than for auditing. The log shows that the agent handles one kind of case well and another poorly, and that turns a hunch into a concrete task, such as a missing article or a configuration change.

What to ask a vendor

"Show me the screen where I can see this." The screen, not the description. It’s one of the biggest differences between products, and it rarely shows up in comparison tables.

Terms used here

How Intake handles it

This question comes from The Intake agent


Questions

Related questions

See every question
  • Can an AI agent act without me reviewing it?

    Yes, and you decide how far it goes. The sensible split is by what can be undone. Lookups change nothing and can run on their own; changes you can reverse can run on their own if they’re logged; and anything you can’t undo, like canceling, deleting or refunding, should be confirmed by a person, because if the agent gets it wrong there, nobody will notice in time.

  • Can an AI agent change a customer’s plan?

    Yes, if you give it that action, although it isn’t always a good idea. An upgrade can be undone, and some companies automate it. A downgrade or a cancellation moves money and doesn’t undo itself, so the sensible setup is for the agent to prepare it and a person to confirm it.

  • Can an AI chatbot handle complex technical support?

    It can handle part of it, the initial diagnosis. An AI agent recognizes the error, checks the state of the account and rules out known causes before the case reaches anyone. What it can’t solve is the problem nobody has seen before, which is what complex technical support is, and why a third tier exists.

Add it without dropping what you use

15 minutes, no commitment