# Tessary groundedness

Groundedness is one of Tessary's built-in classifiers. For each LLM call it checks whether what the
agent said is actually supported by what it was given, scoring the output against its input context.

It catches the shape most production hallucinations take: an answer that asserts things its context
doesn't support while reading as fluent and confident. It runs over every trace at negligible per-
event cost. When it fires, the finding goes to triage, and findings ruled real issues become a case,
so an ungrounded claim that keeps recurring shows up as one investigable pattern with the triggering
traces attached.

## Questions answered under this concept

- [Can a factually correct answer still get flagged as ungrounded?](https://tessary.ai/answers/tessary-groundedness/can-a-correct-answer-be-flagged-ungrounded)
- [Does groundedness check every LLM call, or just the final answer?](https://tessary.ai/answers/tessary-groundedness/does-groundedness-check-every-step-or-just-the-final-answer)
- [Does the groundedness classifier check whether the context itself is correct?](https://tessary.ai/answers/tessary-groundedness/does-groundedness-check-if-context-is-correct)
- [Does the groundedness classifier only work on agents that use RAG?](https://tessary.ai/answers/tessary-groundedness/does-groundedness-only-work-on-rag-agents)
- [What is Tessary's groundedness classifier?](https://tessary.ai/answers/tessary-groundedness/what-is-tessarys-groundedness-classifier)

---

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