Lenz

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

411 followers

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

411 followers

Visit website

AI Infrastructure Tools

•

AI Metrics and Evaluation

•

LLM Developer Tools

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

ClarifyThe autonomous CRM that helps you sell more

Promoted

Lenz Launches

LenzIndependent, multi-model fact-checking API for AI workflows

Launched on August 27th, 2026

LenzFact-check any statement with source-backed, multi-model AI

Launched on April 3rd, 2026

Forum Threads

p/lenz-2

•

3h ago

What would you use Lenz to verify?

Hi Product Hunt

A little over a week ago, you helped Lenz reach #3 Product of the Day. Thank you again - it really meant A LOT to our small team!

p/lenz-2

•

11d ago

We’re #3 Product of the Day and climbing — a big day for a small, bootstrapped team 🔥

A few hours into our launch, Lenz is now sitting at #3 Product of the Day on Product Hunt.

For a small, bootstrapped team, this is a pretty special milestone. We re incredibly grateful to everyone who has checked out the launch, tried the product, asked thoughtful questions, and shared feedback along the way.

p/lenz-2

•

8d ago

We gave 5 frontier LLMs the same 1,000 fact-checks. They disagreed on 63%.

We ve been looking at a question that feels increasingly relevant as more products put LLM output directly in front of users: if two frontier models are asked to judge the same factual claim, how often do they actually reach the same conclusion?

We tested five frontier models on 1,000 real-world claims under the same forced-choice setup.

On 63% of the complete claims, at least one model disagreed with the others or no majority formed.
On 23%, the disagreement was substantive verdicts at least two categories apart.

View all