# Tessary malformed output

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.

## Questions answered under this concept

- [Do I still need this classifier if my model's structured output mode is already on?](https://tessary.ai/answers/tessary-malformed-output/do-i-need-this-if-structured-output-mode-is-already-on)
- [Does Tessary use an LLM to check for malformed output?](https://tessary.ai/answers/tessary-malformed-output/does-tessary-use-an-llm-to-check-for-malformed-output)
- [Is malformed output invalid JSON, or just the wrong shape?](https://tessary.ai/answers/tessary-malformed-output/is-malformed-output-invalid-json-or-just-the-wrong-shape)
- [What is Tessary's malformed_output classifier?](https://tessary.ai/answers/tessary-malformed-output/what-is-tessarys-malformed-output-classifier)
- [Why doesn't malformed_output fire on every call site?](https://tessary.ai/answers/tessary-malformed-output/why-doesnt-malformed-output-fire-on-every-call-site)
- [Why is my agent's output failing the schema it declared?](https://tessary.ai/answers/tessary-malformed-output/why-is-my-agents-output-failing-the-schema-it-declared)

---

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