What data trains a custom classifier?

Your own agent’s production traffic, not a generic public dataset. That’s the point of building one instead of relying on a built-in: a public dataset teaches a check what refusals or errors look like in general, but your agent’s actual failure modes, the policy it has to follow, the tool call it keeps getting wrong, only show up in your own traces.

The examples that shape it come from the behavior you want caught, in your own traffic, so what it scores is the failure you actually have rather than a generic proxy for it. Your traces stay yours either way: Tessary doesn’t use them to train anything shared across customers.

keep reading

More on this.

Can a custom classifier catch a policy specific to my agent?Yes. A custom classifier is fine-tuned to catch the policies, mistakes, and behaviors specific to your agent that a generic built-in check would never see.answer →What's the difference between a custom classifier and a built-in one?Built-ins run the same check on every customer's traffic; a custom classifier is fine-tuned on your own agent's traffic for failures only your agent has.answer →Does a custom classifier cost more to run than a built-in one?No. A custom classifier runs at the same negligible per-event cost as a built-in classifier, on every trace rather than a sampled subset.answer →Everything on tessary custom classifiersThe definition, and every question answered under tessary custom classifiers.concept →

Send us the traces you already emit.

book a demo