A prompt grounding verifier answers the question that matters most in retrieval-augmented and document-Q&A systems: did the model actually stick to the context I gave it, or did it make something up? Hallucinations are rarely obvious — they are fluent, confident sentences that the source never supported. This tool compares a model’s answer against the context you provided and flags sentences whose key terms cannot be traced back, so you know exactly which claims to verify.
How it works
You paste two things: the context (the source text or retrieved documents the model was given) and the answer the model produced. The verifier splits the answer into sentences, extracts the meaningful key terms from each (dropping common stop-words), and measures what fraction of those terms appear in the context. Sentences with strong overlap are marked grounded; those with weak overlap are flagged as potentially unsupported. It reports an overall grounding score and highlights the suspect sentences. All of this runs locally in your browser — nothing is uploaded — so it is safe for proprietary material.
Tips and examples
This is a triage tool: its job is to point you at the sentences worth reading carefully, not to deliver a final verdict. Word overlap will sometimes over-flag a correct paraphrase and can miss a claim that borrows the context’s vocabulary while twisting its meaning, so always confirm flagged sentences by hand. The best fix for chronic ungroundedness is upstream: instruct the model to answer “only using the provided context” and to say “the context does not contain this” when it cannot find support. For audit trails, ask the model to quote the supporting span for each claim, then run the verifier on the result. Use it after every change to a RAG prompt to confirm faithfulness did not regress.