LenzSign off or publish with confidence
Check the facts, figures, and citations in your work.
Whether it’s AI-generated content, a client deliverable, or a research report, Lenz verifies factual statements against primary and authoritative sources or your own reference documents, and checks that the references you cite exist and support what’s written. Every flagged issue comes with evidence and reasoning, so your team spends time only on what needs attention.
- €10,000 warrantyper qualifying check
- Independent public sourcesnever the model that wrote it
- Multiple vendors, three reviewersafter two models argue both sides
“Spotify launched in the United States in July 2009.”
- 01 Framing claim, queries · 3.5 s
- 02 Research 18 public sources · 21.8 s
- 03 Debate for · against · 18.3 s
- 04 Panel Review 3 reviewers · 28.8 s
- 05 Conclusion verdict, score · 8.6 s
Spotify launched in the United States in July 2011.
- techcrunch.com
- theverge.com
- engadget.com
- +15 more
Each stage’s time is this run’s own, replayed faster. A full verification takes ~90 seconds per statement.
Open the full verification01Why independent
A model grading its own output is not an outside check.
AI drafts faster than anyone can check by hand, and asking the model that wrote the text whether its own claim holds up is not an outside check. Lenz sits outside the model vendor and outside your own team. In a full verification it checks each factual statement against public evidence the model was never given: models from several vendors argue both sides and three reviewers weigh the arguments.
A split panel stays visible in the result. The evidence is public, so a customer or an auditor can follow it.
02How it fits
Lenz supplies the verdicts.
Your gate applies your thresholds.
-
A draft is ready
An AI-generated article, a client deliverable, or a research report: anything your team is about to sign off on or publish.
-
Statements are extracted
The text is split into single, self-contained factual statements. Opinions, predictions and questions are left out.
-
Assessed in bulk
A panel of models returns a verdict and a confidence level per statement, synchronously.
-
Uncertain claims are investigated
Negative and low-confidence results escalate to a full verification against independent public sources, with the arguments and reasoning.
-
Your gate decides
What clears your thresholds ships. What doesn't goes to your reviewer with the verdict, sources and reasoning attached. Lenz never holds, edits or publishes your text.
03Research · Open evaluation
Five frontier models, 997 claims, not unanimous on 63%.
Across all answers, models reported 9 or 10 out of 10 confidence 76% of the time. Frozen snapshots, full data, full methodology.
- 632 claims · not unanimous
- 365 claims · unanimous
- n = 997 · one dot per claim
04Warranty
What other AI products tell you: AI can make mistakes. Check important information.
The risk stays with you
Lenz warrants the result.
On the Pro and Scale plans, qualifying checks carry a contractual accuracy warranty, at no extra charge. €10,000 per certificate, €500,000 across all Lenz certificates in any rolling 12 months.
The main conditions- You published a warranted statement, or sent it to someone outside your organisation, after its qualified timestamp.
- A court or regulator later made a finding on the warranted statement that contradicted the verdict, once the time to appeal has passed or appeals are exhausted.
- Damages were awarded against you on that basis.
Fines, penalties, settlements and defence costs are not part of the warranty.
The Great Wall of China is visible from the Moon with the naked eye.
- verdict
- False · 1/10
- confidence
- 9.7/10
- sources
- 29, from 26 domains
- cover
- €10,000 per certificate
- certificate
- fd7dcc7f…566f6deb
- issued
- qualified timestamp
- Namirial,
- OpenTimestamps
- Bitcoin attestation
- record hash
- 3f45d7b2…3e7f1163
05For developers
Four calls and one to run them all.
| Endpoint | What it does | Time |
|---|---|---|
| /extract | Pull verifiable claims out of any text | free |
| /assess | Fast verdict, with the pages it looked at | ~15 s |
| /verify | Full investigation, with verified citations | ~90 s |
| /citecheck | Does each cited source say what the text says | — |
| /review | Issues in a draft's claims and its citations | — |
API reference OpenAPI spec Integrations Connect Claude Connect ChatGPT
# pip install lenz-io from lenz_io import Lenz client = Lenz(api_key="lenz_...") extracted = client.extract(text=model_output) # extract finds up to 100, most check-worthy first; # one assess call takes 20, so this checks the first 20 claims = [c.claim for c in extracted.claims][:20] rows = client.assess(claims=claims).claims if claims else [] # a failed row was not checked: never ship it as clean for c in rows: if ( c.status == "failed" or c.verdict in ("False", "Mostly False", "Mixed") or c.confidence == "low" ): print("HOLD:", c.claim, c.verdict, c.confidence) # HOLD: Python 3.12 runs about 20% faster … False high
// npm install lenz-io import { Lenz } from "lenz-io"; const client = new Lenz({ apiKey: "lenz_..." }); const out = await client.extract({ text: modelOutput }); // extract finds up to 100, most check-worthy first; // one assess call takes 20, so this checks the first 20 const claims = (out.claims ?? []).map((c) => c.claim).slice(0, 20); const rows = claims.length ? (await client.assess({ claims })).claims : []; // a failed row was not checked: never ship it as clean const hold = ["False", "Mostly False", "Mixed"]; for (const c of rows) { if ( c.status === "failed" || hold.includes(c.verdict ?? "") || c.confidence === "low" ) console.log("HOLD:", c.claim, c.verdict, c.confidence); }
curl -X POST https://lenz.io/api/v1/extract \ -H "Authorization: Bearer $LENZ_API_KEY" \ -H "X-Lenz-API-Version: 2026-10-11" \ -H "Content-Type: application/json" \ -d '{ "text": "Python 3.12 runs about 20% faster than 3.11. ..." }' # send the "claim" of each item in "claims" curl -X POST https://lenz.io/api/v1/assess \ -H "Authorization: Bearer $LENZ_API_KEY" \ -H "X-Lenz-API-Version: 2026-10-11" \ -H "Content-Type: application/json" \ -d '{ "claims": ["Python 3.12 runs about 20% faster than 3.11."] }' # hold a row whose status is "failed" (not checked), or whose # verdict or confidence fails your gate
Runs inChatGPTClaudeGoogle Docsn8nZapierCursorClaude CodeMCP serverRESTPython · TypeScript SDKs
06Use cases
Sign off or publish with confidence.
- AI content platformsAI-generated articles and reportsFacts, figures, and citations checked in your pipeline before customer delivery
- Technical B2B content agenciesClient whitepapers and regulatory contentStatutes, compliance deadlines, and vendor claims checked before client review
- Scientific & medical commsScientific & medical communicationsStudy figures, DOIs, PubMed references, and clinical claims checked before peer, client, or MLR review
- Research & advisory firmsResearch reports and regulatory briefsFigures, statutes, studies, and footnotes checked before partner sign-off
Check the next draft before anyone reads it.
Free · 100 assessments or 10 full verifications a month · Zero-retention option