# Tessary custom classifiers

Custom classifiers are classifiers Tessary fine-tunes for your agent. The built-ins cover the
failure modes every agent shares. A custom classifier covers the ones only yours has: the policies
it must follow, the mistakes it actually makes, the behaviors your team already knows to watch for.

They work like the built-ins: cheap enough to run on every trace, scored against a confidence
threshold, and when one fires it creates a finding for further analysis. Each one is trained and
evaluated on labeled examples from your own traffic before it ships, and runs at the same negligible
per-event cost as the built-ins.

## Questions answered under this concept

- [Can a custom classifier catch a policy specific to my agent?](https://tessary.ai/answers/tessary-custom-classifiers/can-a-custom-classifier-catch-agent-specific-policies)
- [What's the difference between a custom classifier and a built-in one?](https://tessary.ai/answers/tessary-custom-classifiers/difference-between-custom-and-built-in-classifier)
- [Does a custom classifier cost more to run than a built-in one?](https://tessary.ai/answers/tessary-custom-classifiers/does-a-custom-classifier-cost-more-than-a-built-in-one)
- [Is a custom classifier tested before it goes live?](https://tessary.ai/answers/tessary-custom-classifiers/is-a-custom-classifier-tested-before-it-goes-live)
- [What data trains a custom classifier?](https://tessary.ai/answers/tessary-custom-classifiers/what-data-trains-a-custom-classifier)

---

Source: https://tessary.ai/answers/tessary-custom-classifiers
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai