Skip to content
Devtoolry
Sign InJoin for Free

AI Citability Checker

Score every section of an article for how easy it is to quote: answer first, self-contained openings, numbers, lists, sources, author and date, with fixes per section.

Something not working, or missing a feature? Send feedback

About the AI Citability Checker

The AI Citability Checker scores how easy each part of a page is to quote. It reads the main content (the <main> or <article> element when there is one), splits it at its headings and scores every section on habits that make a passage stand on its own: a short, direct opening, a named subject instead of "This…", specific numbers, lists or tables, and linked sources. Page-level checks cover the opening summary, structure, evidence, the author and how recently the page was updated.

Our server requests the URLs you enter, like a crawler: it reads the response without running the page's scripts, and the analysis runs in your browser. The URLs and results are not stored.

How to use the AI Citability Checker

  1. Enter the URL of an article, guide or documentation page and press Check citability.
  2. Read the area scores, then open Sections: the weakest are listed first, each with the issue to fix (✗) and what already works (✓).
  3. Rewrite the first sentence of weak sections so it answers the heading directly and names its subject, and add numbers or a source where you make a claim.
  4. Rerun the check after you publish. Use the Blog Post Outline Generator to find the questions your headings should answer.

What each section is scored on

SignalEffectWhy
Short direct opening (8–80 words)+20The first sentence after a heading is the one most likely to be quoted
Opening names its subject+10 (−15 if it starts with "This", "It", "They"…)A quoted passage loses the context that "this" refers to
Specific numbers or measurements+10Specific claims can be checked and are more useful
List or table+10Steps and comparisons are easier to lift from lists and tables
Question heading or definition+5 eachMatches how people ask and how answers start
Link to a source+5Shows where a claim comes from
Under 25 or over 350 wordsCapped at 35 / −15Too thin to stand alone, or too long to quote

Sections start at 40 points and are clamped to 0–100; 70 or more counts as easy to quote. Heuristics written for this tool, not a published standard.

Sources: Google: Optimizing your website for generative AI features, Google: Creating helpful, reliable, people-first content

Works well with the AI Citability Checker

Frequently asked questions

What makes a passage citable?

It makes sense on its own: the first sentence answers the question in the heading, the subject is named rather than referred to as "it" or "this", and claims come with specifics (numbers, dates, names) and a source. These are the same habits that make text easy to skim for readers.

Should I split my content into small chunks for AI?

No. Google says you do not need to chunk content or write in special phrasings for its AI features. Write clear sections under descriptive headings; the checker only flags sections that are very short or very long so they stay readable on their own.

Why is a section scored low when it reads well?

The rules are simple text heuristics. A section that opens with "This is why…" or has no specifics scores lower even if it flows well in context. Treat the score as a pointer to sections worth a second look, not a verdict.

Which part of the page is analysed?

The <main> element, or a single <article>, or else the body without its header, footer, navigation and sidebars. The report says which one was used and how many words it found.

Related tools