Read AI answers with a clear head.
Sereno checks whether the source actually says what the AI claims, not just whether a source exists.
A quiet overlay for ChatGPT, Claude, and Gemini that flags claims that aren't backed up, explains why, and points you to the sources.
The Eiffel Tower was completed in 1889 for the World's Fair in Paris.
It stands exactly 410 meters tall, making it the tallest structure in France.
Source: toureiffel.paris listed height: 330 m
A citation isn't a guarantee.
AI assistants sound confident and often attach sources. But a source being present doesn't mean it supports the claim. Citations get misattributed, stats get invented, and sometimes the linked page says something different, or nothing, about what the AI told you. The more an answer matters, the more that gap costs you.
What Sereno does
Watches the answer.
As you read a reply in ChatGPT, Claude, or Gemini, Sereno reads along and identifies the factual claims.
Checks the support.
It looks at whether each claim is actually backed by a credible source, the one cited, or one it finds, rather than assuming a citation means it’s true.
Flags the gaps.
Claims fall into three honest states: Supported, Likely unsupported / contradicted, or Unverifiable. Sereno marks them inline, explains its reasoning in plain language, and links you to sources so you can decide for yourself.
When Sereno isn't sure, it says “unverifiable”, it won't pretend a claim is false.
Everyone shows you a source. Sereno tells you whether it holds.
The big AI tools are racing to attach citations to their answers. Almost none of them check whether the citation actually supports the claim, that's the gap Sereno lives in. And because Sereno works across ChatGPT, Claude, and Gemini, it sees what no single AI tool can: it can hold an answer up against the wider web instead of grading its own homework.
What Sereno is for
Sereno has one job: to help you judge the reliability of the claims in AI chat responses by checking them against sources. It reads the content of the AI conversation you're viewing solely to perform that check and show you the result. It does not block content, inject ads, track your browsing across the web, or sell your data. See our Privacy Policy for exactly what it accesses and why.
Try it
Sereno is in early access while our Chrome Web Store listing is under review. Right now we're sharing it with a small group of people who want to read AI answers more carefully.
Coming soon
A one-click install from the Chrome Web Store is on the way.
Questions
Does Sereno read my conversations?
Yes, it reads the content of the AI chat you're actively viewing, only to check the claims in it. We don't sell that content or use it for advertising. Details in our Privacy Policy.
Which AI tools does it work with?
ChatGPT, Claude, and Gemini to start. More to come.
Is Sereno always right?
No, and it won't pretend to be. It tells you when a claim isn't supported and, just as importantly, when it can't tell. Treat its flags as a prompt to look closer, not a final verdict.
Is it affiliated with OpenAI, Anthropic, or Google?
No. Sereno is an independent tool and isn't endorsed by any AI provider.
What does it cost?
It's free during early access.