Lenz
Independent, multi-model fact-checking API for AI workflows
Start new thread

Lenz - Independent, multi-model fact-checking API for AI workflows

by
•
Lenz is an AI fact-checking API for products that cannot afford to hallucinate. It extracts verifiable claims from any text, then checks each one: searching independent sources, running multi-model debate, and routing through a review panel — returning a scored verdict with every source, argument, and step visible. Most AI tools give you one model's best guess from memory. Lenz ensures no single model's blind spots drive the conclusion. Available as API and MCP. Try it free at lenz.io/ph

Add a comment

Replies

Best
Congrats on the launch! So how do you validate the checks?
Maker

, this is how the validation itself works at a high level:
Beyond the verdict, we provide full analysis details (sources, citations, reasoning, etc.), so you can verify the verification. Happy to share more details if you are interested.

fact checking as an api is underrated 🔍 media or legal buying first?

Maker

, indeed! Using a deep fact-checking layer makes the most sense when reputational, legal, or financial risk is involved. So yes - media, legal, finance, healthcare.

Wow. That's super cool. I read pitch decks all day and a lot of what's in them is forward-looking "market will be $1T by 2030" kinda of claim. Does Lenz work for that too? They usually have a market data source as the basis for their claims.

Maker

, one of our clients is a fund, and they use Lenz in exactly this way. They have their own prescreening AI tool and connected Lenz to it to help fact-check founders' claims in the decks. Lenz cannot check the internal company traction information since this is not public information, but it does a really good job verifying the claims about the market - market size, growth projections, competitors, etc.

This feels especially important right now. We are living in a world where AI is becoming one of the first places people go to check what is true, yet your research shows that frontier models disagree on 63% of real-world fact checks.

That is such a powerful reminder that a confident AI answer is not the same thing as a verified answer.

Really love what you’re building with Lenz. The need for trustworthy verification is only going to grow as AI becomes more embedded in how we work, learn, and make decisions.

At this point, I’m just happy to have an AI that occasionally says, “Let me check that” instead of confidently making things up 😂

Maker

 Indeed. In our experience, the models' self-reported level of confidence in their answers is mostly noise. They aren't trained to self-assess. Even worse, their incentives (to keep the user happy and engaged) push them to show high confidence when asked. On a 1-10 scale, in 76% of answers, the models report confidence of 9 or 10. And the correlation between confidence level and how much they agree with each other is not too strong either:

First
Previous
12