Lenz

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.

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

Congrats on launch number two. Publishing the data and prompts for anyone to pick apart is a good look.

Half the pages that rank for file format questions I work on are confidently wrong, and they're the most linked. How do your source ratings handle a topic where the crowd is wrong?

Congrats on the launch! Does your product provide the full chain of sources for manual verifiability? (not just direct links, but maybe logical facts if this -> then this -> hence this )

Congrats team..idea of having a jury review the evidence is quite interesting.

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 😂

Congrats on the Launch @kostaj This hits close to me, spent Years in Security Testing and the same problem shows up there: one Models blind spot becomes everyones blind spot if you don't cross check.

Congrats on a launch, team @kostaj @vicky_dodeva @david19782 @pavel_j - are you a family, wow?I have a question regarding the product as well. Could Lenz verify outputs from Deep Research in ChatGPT?

Love the idea and positioning! Excited to see where it goes huge congrats on the launch

Hi, Vicky here 👋 the non-tech co-founder of Lenz AI has genuinely changed what I can do on my own (from ops to marketing to building alongside an engineering team without being one). I’m one of those people it has really opened doors for.But there’s another side to this. More and more companies rely on AI to produce the actual content their customers see: reports, articles, recommendations, research, support replies, ... And "someone will check it before it goes out" stops working at scale.That’s the part of Lenz that really resonates with me. For editorial and production teams, that means letting verified claims through, sending uncertain ones for human review, and keeping the sources behind every decision.AI will let us produce vastly more. Verification has to scale with it.Very excited to have Lenz out here today and would love to hear your use cases.

Hi, I'm Pavel, part of the Lenz team. I worked on the MCP server and the CLI amongst other things.Quick note on why we believe this needs to exist: we gave the same 1,000 real claims from Lenz to 5 frontier models (Fable, GPT 5.6, Gemini 3.1 Pro, Sonar Deep Research, Grok 4.5), identical prompt, all with web search and thinking. All five agreed on only 37% of them, and on 23% the verdicts were 2+ steps apart on a 5-point scale. Surprisingly confidence was almost meaningless: 76% of all answers were self-rated at 9 or 10 out of 10. The figure below is that result. Each ring is a model, each spoke is a claim, grouped by agreement.The two services I built:- MCP server at lenz.io/mcp. To connect see lenz.io/integrations/mcp-server or just hand it to your agent.- CLI: pipx install "lenz-io[cli]", then lenz verify "the Great Wall is visible from space"Paper, data and prompts are open if you want to pick it apart: lenz.io/research/llm-disagreement/v1.1Happy to answer anything. Let me know if you try the MCP.

Tried it, pretty cool! Couldn’t extract claims from a YouTube video though. Text input worked seamlessly.

Kosta here, co-founder of Lenz. Many businesses ship AI-generated content to their customers. Some of those use cases could benefit from factual verification of that AI output. That's why we built Lenz, packaged it as an API/SDK, and made it available across multiple platforms (n8n, Zapier, MCP, CLI), so people can easily integrate it into their workflows. Lenz verdicts come with a full audit trail - sources, citations, reasoning, confidence. How Lenz is different than just asking a model:(1) separate evidence gathering step (with source ratings) that doesn't rely on the model's memory or retrieval capabilities(2) multi-vendor, multi-model approach to address single-model biases(3) multi-round adversarial debate to crystallize the strongest for/against arguments(4) multi-model jury reviewing the evidence and the debates across multiple axesKey API primitives: /extract - extracts the factual claims from a text; /assess - quick assessment of a claim; /verify - the full deep claim verification; /ask - follow-up post-verification questions.We measured the level of disagreement between the individual frontier models: on 23% of real-world claims, they disagree significantly, which sets the floor of the error Lenz is built to address.To try a Lenz verification via the UI: lenz.io/verifyMore about the LLM disagreement research: lenz.io/research/llm-disagreementTo integrate Lenz: lenz.io/integrationsGitHub: github.com/lenzhqHope you find this useful. Let me know either way :)