Claim vs evidence
Does the evidence support the claim, contradict it, or not settle it? With the sentence that decides.
The judging step of a fact-checker or a research agent: one claim and the text you found for it. Jev says whether the evidence supports the claim, contradicts it, backs only part of it or doesn't settle it, checks that numbers, dates and names match, and quotes the sentence that decides. Extract claims and search however you like; this is the step that has to be right.
Try it live
Real calls to Jev. Pick an example or paste your own.
Pick an example or paste your own input, then run it.
Under the hood
Every question and rule, in the open. Fork it to change any of them.
What it asks
Reads claim and evidence, then asks 3 questions in one call.
- Q1StancePick one
Taking the
evidenceat its word, what does it say about theclaim?SupportsContradictsPartlyDoesn't say - Q2One sentence decides itYes / no quotes evidence
Does a single sentence of the
evidencesettle theclaimon its own? - Q3Details matchYes / no
Where the
claimgives numbers, dates, names or places, does theevidencegive the same ones? If theclaimhas none, answer yes.
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1If Stance is Contradicts and Stance: confidence ≥ 0.5Contradicted
- 2If Stance is Supports and Stance: confidence ≥ 0.6 and Details match ≥ 0.5Supported
- ·DefaultNot settled
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/evidence-check/run.
curl -X POST https://tryevally.com/api/v1/judges/evidence-check/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "claim": "The Hubble Space Telescope was launched in 1990.", "evidence": "The Hubble Space Telescope was carried into low Earth orbit in April 1990 aboard the Space Shuttle Discovery. It is still in operation." }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
More in AI output quality
- AI output quality
RAG answer grader
Is the answer grounded in the retrieved source, and does it answer the question?
PassNeeds reviewFail5 questions - AI output quality
Hallucination detector
Catch invented numbers, names and claims before your users do, with the sentence quoted.
GroundedSuspectHallucinated4 questions - AI output quality
Citation checker
Does the cited passage actually support the claim it's attached to?
SupportedPartly supportedUnsupported+12 questions - AI output quality
Summary checker
Faithful, complete and free of added opinions: the three ways summaries go wrong.
Good summaryNeeds editsUnfaithful5 questions - AI output quality
Support reply grader
Check an AI support reply against the customer's message and your policy before it's sent.
Ready to sendEdit firstEscalate+15 questions