Audit-grade fact-checking for AI-drafted text.A fact-checking API for AI output, for teams that can't afford a hallucination. Check it before a customer or a client reads it, and flag uncertain claims for your team.
For teams shipping AI-drafted text
Built for automated content workflows and AI agents that draft and review.
Newsletters, briefs and posts
The claims, numbers, dates and names in a draft, before it goes out→
Tax and legal memos
Forms, deadlines, thresholds, what a court held→
Model-generated answers
The factual statements in an answer, before a customer sees it→
Market and competitor claims
Market figures and competitor prices checked against public sources→
Four API calls, one escalation path
Extract the statements, assess them in bulk, escalate the uncertain results to a full verification for the sources and the reasoning, ask follow-up questions. From Claude, Cursor, a script, n8n or Zapier.
/extract
Pull verifiable claims out of any text
/assess
Fast multi-model verdict for sync UX
/verify
Full adversarial pipeline with citations
/ask
Follow-up Q&A grounded on a verification
Warranty
Vendors disclaim accuracy. Lenz warrants the verdict.
On a paid Developer or Scale plan, every full verification that qualifies carries a contractual warranty, at no extra charge.
How the warranty works →
Research
Five frontier models, 1,000 real claims, no agreement on 63%.
Our open evaluation of LLM agreement on real fact-checks: frozen snapshots, full data, full methodology.
Read the report →