Can a custom classifier catch a policy specific to my agent?

Yes, that’s what a custom classifier is for. The built-ins cover failure modes every agent shares: frustration, malformed output, secret leaks. A custom classifier covers the ones only yours has, the policy it has to follow, a mistake it actually makes, a behavior your team already knows to watch for and has never had a check on.

Examples of the kind of thing this catches: a support agent that isn’t allowed to promise a specific refund amount, a coding agent that shouldn’t touch a particular file path, a booking agent that has to confirm a date before finalizing it. None of those are failure modes a generic classifier would know to look for, because they aren’t generic, they’re yours. A custom classifier is trained on your own traffic specifically so it can catch them.

keep reading

More on this.

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 →Is a custom classifier tested before it goes live?Yes. Every custom classifier is trained and evaluated on labeled examples from your own traffic before it ships and starts scoring live traces.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