We got tired of answering the same question.
Peeve started because a help center is a description of a product at a moment that has already passed. The product moves; the description doesn't. Every support team in the world is paying for that gap in hours.
So instead of describing the interface, we read it. Every session is a measurement, and the measurements are what keep the answers true.
I ran support on Intercom with around 150 help articles. The product kept changing; the articles did not. So every AI support tool leaned on stale knowledge, and users asking a simple how-to question got a long paragraph describing an interface that had already moved. Reviewing those conversations, finding what failed, and rewriting the help center became its own full-time job.
The answer to a how-to question should not be a wall of text. So we stopped describing the interface and started reading it. Peeve builds a living brain of the product, then answers, shows, does, or escalates, depending on what is safest and most useful. When it cannot do something safely, it says so and hands off. It never guesses.
