# Claims and sources checker > For the complete documentation index, see [llms.txt](https://attensira.com/llms.txt). > Every page on this site is also served as Markdown: append `.md` to any URL, or send `Accept: text/markdown`. > Find every claim on a page that carries a number or borrows authority, and see what sources it on the page, if anything. Free, no sign-up. - Canonical page: https://attensira.com/tools/claims-source-checker - Source: converted from this page's own HTML. It carries no claim records, because the page is not a content-pipeline entity. The claims and sources checker reads one page and finds every claim that carries a number or borrows authority, such as a percentage or a study. For each it shows what, if anything, sources it on the page. A claim with nothing beside it leaves a reader, or an assistant, nothing to check it against. Free, no sign-up. Our run attensira.com Input attensira.com/blog/zero-click-search - Words read: 4,479 - Claims found: 6, all percentages - Linked source in the same block: 2 of 6 - ✓ Passes - A date and nothing else: 4 of 6 - ◐ Weak - Nothing at all: 0 of 6 - ✓ Passes Show all 5 rows Show the first 4 Claims and sources checker, production, n=1 run · 4 Oct 2026 Or use the free tool below ## Check a page Seconds, on our server · Free, no sign-up Page URL Check the claims on this page It looks for the same claim shapes our own content gate looks for before a page of ours publishes, then reports what sits beside each one. **It never opens a link and never decides whether a claim is true.** Give it a page and it splits the visible text into blocks, then into sentences, and flags every sentence carrying a percentage, a multiplier, a money figure, an “N in M” ratio, or a phrase that borrows authority without naming anyone. For each one it reports what shares that block: a link off-site, a link back to your own pages, a `cite` element, a footnote marker, wording like “according to”, or a date. If nothing does, it says so plainly. Your result appears here - Words read - Claims found - Linked source in the same block - A date and nothing else - Nothing at all See our own run Share ## What does it look for? 1. ### Claims Five shapes in every sentence: a percentage, a multiplier, a money amount, an “N in M” ratio, and “studies show” wording that names no one. 2. ### Links around the claim Links off-site and links back to the same site, in the block the claim sits in. 3. ### Other sourcing Footnote references, cite and time elements, bracketed markers, attribution wording and dates. ## What does it find on one of our own posts? We ran it on attensira.com/blog/zero-click-search, a statistics-heavy post from before the rebuild. > One of the four, verbatim > > In 2024, an estimated 65% of global Google searches were zero-click. Four of six numbers in our own post say when, not who. “An estimated 65%” estimated by whom is the question nobody can answer from the page, a reader or an assistant. The checker is a pattern match and it says so. On attensira.com/methodology the same day it flagged two sentences about reporting “0%”, which are rules, not statistics. Read each flag before you act on it. The run is the result panel at the top of this page. Read on 4 Oct 2026. About this tool - You give it: One URL - It runs: Seconds, on our server - It keeps: About an hour in a shared cache keyed by the URL; nothing tied to you - Cost: Free, no sign-up - Our own run: attensira.com/blog/zero-click-search · 4 Oct 2026 Details ## How does it find a claim and read its sourcing? The page is fetched once, server-side, as Attensira. Everything inside `script`, `style`, `noscript`, `svg`, `template`, `head`, `iframe` and `canvas` is discarded. What survives is split into blocks (one paragraph, list item, heading, table cell, blockquote or caption each) and then into sentences. Each sentence is matched against five shapes: a percentage, a multiplier, a money amount, an “N in M” ratio, and phrases that assert somebody found something without naming who. Then the block around the flagged sentence is read for sourcing: links off-site, links back to the same site, in-page footnote references, a `cite` or `time` element, a bracketed footnote marker, attribution wording, and dates. ## Why did we build it for ourselves first? The claim patterns are our own content gate’s, turned outward. Every page in our content tree is checked by that gate: a number in prose needs a claim entry behind it carrying a source URL and the date it was retrieved, or the sentence is rewritten qualitatively. Posts carried over from our old site only warn until they are rewritten, which is how the post in the example above still has four numbers with a date and no source. We wrote it after finding unsourced numbers in our own drafts: the kind that get repeated, cited and quietly become facts. The sourcing half cannot be the same on your page, and we will not pretend it is. Our gate reads a declared source and a retrieval date we hold alongside the text; on a page we only fetched, all we can see is what shares the block with the sentence. That is a weaker test, and it is the strongest one available from the outside. The rules that check produces are published rather than described: [how Attensira reports the numbers it publishes](https://attensira.com/methodology) states them, including the ones that make a page refuse to render rather than show a figure it cannot stand behind. It matters more now than it did for search. An assistant asked “how big is this market” can lift a figure from a page that carries no source, attribute it to your brand, and repeat it to the next person who asks. The number becomes yours the moment it is quoted, whether or not you made it up and whether or not you can defend it. The method - Fetched: Once, server-side, as Attensira - Claim shapes: 5: percent, multiplier, money, N in M, unnamed finding - Sourcing read from: The block around the sentence Our own gate - A number in our prose needs: A source URL and a retrieval date - On your page it can see: Only what shares the block - Our rules: [Published](https://attensira.com/methodology) ## What happens to an unsourced number inside Attensira? Inside Attensira, a claim is never changed on its own: any edit that touches a number, a price, a product or a competitor name is filed for your approval in every approval mode, Act included. [Approval modes](https://docs.attensira.com/agent/approval). Software that does your AI-search visibility work, with you in control of every change. ## How do you fix what it finds? - **Nothing in the block sources it.** Either link the primary source in the same paragraph (not in a references section three screens down), or rewrite the sentence qualitatively. “Most buyers now start in an assistant” needs no source; “63% of buyers do” does. - **Only links to this same site.** Fine when the link leads to your own published research with its method and sample on the page. Not fine when it leads to a product page, which has no method or sample to check. - **Names a source in words, links nothing.** “According to a recent report” is unfollowable. Name the publisher, the year and the report, and link it. - **A date, and nothing else.** A date answers when, not who from. It is worth keeping (a 2019 figure presented as current is its own problem), but it is not the source. - **An appeal to authority with no authority named.** “Studies show” and “experts agree” read as evidence but give a reader nothing to follow. Name the study or drop the appeal. - **Claims in the nav, header or footer.** These are flagged too. When that markup repeats site-wide, a price or a statistic in it is a claim repeated on every page. ## Questions people ask about this check What it will not claim - A link in the same block is not verification: we never open it. - A sentence it did not flag is not a sentence it approved: it is a pattern match. - There is no score: the reading of each flag is yours. ### Does this tell me whether the claims on my page are true? No, and nothing that fetches a page once can. It tells you which sentences assert something checkable, and whether a reader standing at that sentence has anywhere to go to check it. Truth is downstream of that, and it needs a person who reads the source. ### Why flag a sentence that has a link right next to it? Because a link is presence, not proof. The verdict distinguishes between a link that leaves your site, a link back into your own pages, wording that names a source without linking it, and nothing at all. A claim with an off-site link is reported as exactly that: sourced in the block, unread by us. ### Why does it skip whole sentences I know are claims? It matches five shapes and nothing else. A qualitative claim, a comparison with no number, a promise about outcomes, or a statistic written out in words (“two-thirds of buyers”) will not match. Treat the list as a floor: these are the claims a pattern can find, not all the claims on the page. ### The page looks empty to the tool but full in my browser. Why? We do not execute JavaScript, and neither does a crawler that fetches your raw HTML. If your body is assembled in the browser, the text a model sees is the text we saw: very little. That is a finding about how the page is served, and the [page token inspector shows the same gap](https://attensira.com/tools/page-token-inspector) from the retrieval side. ### Do you store the pages I check? Not against you. There is no account, no email field and no history you could be looked up in, and nothing here observes what any assistant fetches. We read the page ourselves, once, because you asked. The findings are held for about an hour in a shared cache keyed by the URL, so an identical check in that window is answered from the cache instead of fetching the page again. ## This finds the claims. Attensira's crew sources them, with your yes. ## Tell it where you want to be cited.