How is this check scored?
Every threshold on this page comes from one source: the citation-readiness scorer Gadex publishes. Per Gadex's own build, the weights below are read directly from that scorer and a test fails the build if the documented figure stops matching the applied one. A pass earns the full 14 points, a warning earns half, a fail earns none.
| Result | How it is decided |
|---|---|
| Pass | The first body paragraph is 40 to 320 characters. |
| Warn | The second paragraph fits that range but the first does not. |
| Fail | Neither of the first two paragraphs is a self-contained answer of that length. |
Why does this check exist?
An extraction step has to choose a span. The opening paragraph is the cheapest, most reliable guess, which is why a page that answers its own question there is disproportionately easy to quote.
The upper bound matters as much as the lower one. Past roughly 320 characters a paragraph stops being liftable as a unit and starts being something a model has to summarise — and a summary is a paraphrase, which is far less likely to be attributed back to you.
The lower bound rules out a fragment. Under 40 characters there is no answer, just a heading in paragraph clothing.
How do you fix it?
- State the answer in the first paragraph, in one or two sentences, before any context or preamble.
- Move scene-setting below the answer. "The search landscape has shifted considerably in recent years" is not an answer to anything.
- If the page genuinely answers several questions, it is probably two pages. Split it and let each open with its own answer.
How often do pages fail this check?
Per Gadex's own measurement across the 91 content pages on this site, using the checker published at /tools/ai-search-visibility-checker/: 71 pass, 18 carry a warning, and 2 fail. Per that same run, 22 per cent of Gadex pages have something to fix on this check alone.
Those figures include the pages Gadex fails. A checker whose author exempts itself from the checking is marketing rather than measurement, so the numbers are generated from the built site on every deploy and the build fails if the published figures stop matching what Gadex actually scores. When Gadex fixes pages, the numbers move on their own.
What does this check miss?
- Bylines, dates, share prompts and short category labels are skipped before the opening paragraph is identified, so page furniture does not get mistaken for the lede. Without that, a template printing an eyebrow above the H1 would push every good answer into second place.
- The check measures length and position, not correctness. A confident wrong answer of 200 characters passes.
- It cannot tell whether the opening paragraph answers the question the title asks. That judgement is yours.
Where does this guidance come from?
The scoring rules are Gadex's. The reasoning about why these properties matter draws on the platforms' own published guidance:
- Google Search Central: creating helpful, reliable, people-first content — on self-evident expertise, sourcing, and who the content is for.
- Google Search Central: Article structured data — on author and date fields, and what they are used for.
- OpenAI: bots and crawlers — on how ChatGPT fetches and attributes pages it surfaces.
How we measured this
The counts above come from running the Gadex scorer over the built HTML of every content page on this site, reading each page's main content region only — nav, header and footer links are excluded, because a visitor pastes an article rather than a whole document. Legal boilerplate, the 404 page and generated tool result renderings are excluded as pages where the score would be meaningless. Per that run, the 91 pages counted are the ones a reader could plausibly ask an assistant to summarise.
The scoring thresholds on this page are read from the same module the tool runs, and a test fails the build if the weight documented here stops matching the weight the scorer applies. What none of this can tell you is whether an answer engine will cite a page: citation depends on the model, the prompt, the index and the competing sources, none of which is visible in your markup.
Common questions
Does this mean every page has to start with a definition?
No. It means the first paragraph should resolve whatever the page promises. For a how-to that is the outcome and the constraint; for a comparison it is the recommendation. A definition is only the right opening when the page is a definition.
Our opening paragraph is deliberately long and sets up the whole piece. Is that wrong?
Not wrong, but it costs you extractability. A long opening reads well to a human who has already decided to read. It gives a retrieval step nothing clean to lift. Putting a short answer first does not prevent you from writing the longer setup second.