ProductSign 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 identifies the factual statements it can check against primary and authoritative sources or your own reference documents, and checks that the references you cite exist and support what’s written. You get a result for each, with the evidence and reasoning behind it.
01Example
Three statements in one paragraph. One is wrong.
| Claim | Verdict | Lenz Score | Sources |
|---|---|---|---|
| OpenAI released GPT-4 in March 2023. | Truehigh confidence | 10/10 | go.nature.comreuters.comapnews.com+9 more |
| OpenAI was founded in 2015 as a nonprofit research laboratory. | Truehigh confidence | 10/10 | storage.courtlistener.com990s.foundationcenter.orgtechcrunch.com+16 more |
| GPT-4 had a context window of 128,000 tokens at its release in March 2023.Suggested rewriteGPT-4 had a context window of 8,192 tokens at its release in March 2023. | Falsehigh confidence | 1/10 | openai.comweb.archive.orgdevelopers.openai.com+10 more |
Deep check · Checked 7 September 2026.
Open a row for the sources it used and the reasoning that weighed them.
Open a deep check to see which release the sources actually describe, and the reasoning that weighed them.
02Use cases
Built around the work you sign off or publish.
- AI content platformsAI-generated articles and reportsFacts, figures, and citations checked in your pipeline before customer delivery
- Content agenciesClient deliverables and medical contentWhitepapers, regulatory explainers, and pre-MLR drafts checked before client review
- Research & advisoryResearch reports and regulatory briefsFigures, statutes, studies, and footnotes checked before partner sign-off
03What Lenz checks
Check facts, citations, and your reference documents.
Facts and figures
Dates, numbers, rankings, thresholds, and factual claims—each checked against primary and authoritative sources. Opinions and recommendations are left alone.
Citations and references
Checks whether a cited URL, DOI, statute, or EU act exists (or a cited case resolves) and whether its text supports the sentence attached to it.
Your reference documents
Through the API, check a draft against your own brief, dataset, or source pack alongside public sources. Those checks stay private.
04Where you work
Use Lenz where you write, or wire it into your pipeline.
-
In Word and Google Docs
In the Workbench on a desktop, upload a Word document or paste a Google Doc link, and download the file with Lenz’s comments and suggested edits. In Google Docs, the Lenz Fact-Checking add-on checks the draft inside the Doc.
-
In ChatGPT and Claude
Connect Lenz to ChatGPT or Claude with one sign-in and no API key, then ask the assistant to check the draft or answer in front of you.
-
In n8n, Zapier, and the API
Add a pre-publish check step in n8n or Zapier, connect coding agents over MCP, or call the REST API from Python or TypeScript.
05Two checks
A fast first read, then the full investigation.
~15s
Quick check
A fast verdict from a three-model panel, how confident it is, and the pages the reviewers looked at. Use it to sort the statements in a long draft.
1–2min
Deep check
Lenz investigates the claim in about a minute or two: it researches independent sources, has two models argue both sides, and has three independent reviewers score the evidence. You get a verdict, a score from 1 to 10 (or “No Public Record”), the sources, the reasoning, and a suggested rewrite when a detail is wrong. When the deep check changes the quick verdict, rely on the deep check.
Public sources and supported registries, plus any reference documents you supply through the API. Text only. Lenz does not judge whether the text was machine-written.
Warranty
Vendors disclaim accuracy. Lenz warrants the result.
A verdict can qualify when a full verification returns True or False with high panel confidence and enough independent sources behind it.
On a paid Pro or Scale plan, every full verification that qualifies carries a contractual warranty, at no extra charge.
06Pricing
Try free, no card.
$7.99/ month
500 quick checks or 50 deep checks a month, in any combination.
Or $6.59 a month, billed $79 a year
Choose Plus$99/ month
5,000 quick checks or 500 deep checks a month, in any combination. The warranty on qualifying verdicts.
Or $83 a month, billed $990 a year
Choose Pro$399/ month
20,000 quick checks or 2,000 deep checks a month, for production volumes. The warranty on qualifying verdicts.
Or $333 a month, billed $3,990 a year
Choose Scale