QEAR verifies each claim against the actual source text and returns the exact citation — or honestly abstains when nothing supports it. It never makes up a verdict. Live today for GDPR: paste a legal statement, get each sentence checked against the regulation with the article cited.
QEAR retrieves the actual regulation, verifies each claim against it, and cites the exact provision. When a claim isn't supported by any source, it says so — instead of inventing a verdict.
That honest abstention is the whole point: it's what makes the "supported" answers trustworthy. Live today for GDPR, with more jurisdictions on the way.
# Check a GDPR claim against the regulation curl https://api.qear.ai/v1/verify_legal \ -H "Authorization: Bearer qe_..." \ -d '{ "jurisdiction": "EU", "answer": "Once consent is given under the GDPR, it can never be withdrawn." }'
{
"verdict": "refuted",
"claim": "consent can never be withdrawn",
"citation": "GDPR Art. 7(3)",
"reasoning": "The regulation grants the
right to withdraw consent at any time —
directly contradicting the claim.",
"url": "https://gdpr-info.eu/art-7-gdpr/"
}
For questions outside a grounded corpus, QEAR offers an experimental open-domain check that classifies how an answer is uncertain — returning one of five diagnostic classes and a recommended action. It verifies against a generated reference rather than authoritative source text, so it’s a triage signal, not a citation. For anything you need to stand behind, use grounded verification above.
High confidence in the consensus answer. Trust the result and ship it.
Candidates split on wording but agree on substance. Normalization resolved it; trust the result.
Different dates, names, or values for the same fact. Do not trust — verify externally or escalate to human review.
Most candidates refused to answer or said the question is unanswerable. Trust the refusal.
Candidates returned defaults (0, N/A, none). The model is producing convention rather than knowledge.
We'd rather tell you the truth than sell you a tool that fails on your use case. Code verification is on our roadmap — join the waitlist.
| Feature | QEAR | Competitor APIs | Native logprobs |
|---|---|---|---|
| Numeric confidence score | Yes | Yes | Token-level |
| Uncertainty classification | 5 classes | No | No |
| Human-readable diagnosis | Yes | No | No |
| Grounded legal citation | Yes | No | No |
| Recommended action per response | Yes | No | No |
| Adaptive compute routing | Yes | No | No |
| Model agnostic | Groq + OpenAI + Anthropic | Varies | Proprietary |
| Peer-reviewed methodology | Nature 2024 | Proprietary | Standard |
QEAR extends the semantic entropy methodology from Farquhar et al. (Nature, 2024) with three original engineering contributions, validated across three model scales:
Start free with 1,000 verification claims a month. Pay only when you need more. No surprise fees. No "contact sales" for tiers under enterprise.
Add QEAR to your AI pipeline with a single HTTP call. Works in any language — Python, Node, Go, Ruby, anything that speaks HTTP.
# Add 5 lines to your existing app r = requests.post( "https://api.qear.ai/v1/verify", headers={"Authorization": f"Bearer {KEY}"}, json={"prompt": q, "answer": ai_answer} ).json() # → r["uncertainty_class"], r["diagnosis"]Get API key
Not a developer? Paste your question and the AI's answer into the playground and get the same diagnosis instantly. No code, no integration. Perfect for double-checking ChatGPT or Claude on important work.
Sign up for an API key in 30 seconds. Or try QEAR in your browser with no signup at all. Either way — see the diagnosis in action.