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.
1 question
Answered, plainly.
Two ways to run Tessary.
Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.
Tessary Cloud
We host it for you. Send your first trace with nothing to deploy and no model key.
- traces
- 10,000 per calendar month
- stored trace data
- 1 GB
- retention
- 30 days
- model credit
- $10, one-time, for triage and root-cause analysis
- credit card
- not required
Self-hosted Tessary
Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.
Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md
docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y