Tessary
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.
5 questions
Answered, plainly.
Can a factually correct answer still get flagged as ungrounded?Yes. Groundedness checks whether an answer is supported by its context, not whether the answer is true, and those are different questions.answer →Does groundedness check every LLM call, or just the final answer?Every LLM call. It scores each call against its own context as the call happens, not just the last message a trace sends back to the user.answer →Does the groundedness classifier check whether the context itself is correct?No. It checks whether the answer matches the context given, not whether that context is accurate, so a wrong or stale source can still score grounded.answer →Does the groundedness classifier only work on agents that use RAG?No. It scores any LLM call against whatever context that call received, tool outputs and prior turns included, not only retrieved documents.answer →What is Tessary's groundedness classifier?A built-in classifier that scores each LLM call against the context it was given, catching answers that assert things the context doesn't support.answer →