malformed_output is one of Tessary's built-in classifiers, a deterministic one: checks that pass or fail, no judgment involved. When a call site declares a structured output, Tessary captures its schema and validates each output against it.
It catches exactly the failure your calling code would hit in production: output that doesn't parse, or parses but violates the declared shape. Every firing is high confidence, since the output either matches the schema or it doesn't, and detections carry the violation messages as evidence. Where validation isn't meaningful, it stays quiet. Detections go to triage, where the ones ruled real issues become cases.
6 questions
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