Free AI-visibility audit
Can AI assistants find, read and cite your page?
Paste a URL. Citation Ready fetches it the way a citation crawler does and returns a 0 to 100 score with the three fixes that matter most.
It measures whether the exact URL answers 200 on a host Bing can rank, whether the answer is in the raw HTML with a labelled answer paragraph and a visible date, and whether the structured data says what the page is and when it changed. Every check is weighted by what we measured on our own network of about 60 sites over six weeks of Copilot and ChatGPT citation data. It is a readiness score, not a prediction that any engine will cite you. Every result shows the actual value found, and a failed fetch is reported as a failed fetch.
Sample reports: askhistoryai.com history-books guidewatchshowdown.com Casio Duro vs Seiko 5 Sports
See how a competitor scores: every report has a compare form that puts two pages side by side, group by group. Example comparison. Every audited host also lands on the public leaderboard, and each report hands you an embeddable score badge.
How the score works
Updated 2026-09-0535 checks in four groups. Each check passes, warns or fails; the score is the weighted share of credit earned (pass counts in full, warn counts half) out of 143 weight points. The two groups about fetching and about the raw HTML carry most of the weight because that is where the measured data showed pages winning or losing. Every check has a page of its own with why it matters and how to fix it.
Platform subdomains with Bing impressions
Every *.pages.dev site we run had zero, and every site with impressions had its own domain. A custom domain is the gate.
Edge requests that never run JavaScript
The answer has to be in the raw HTML. An empty app shell has nothing to cite.
Words on a page that earned 10 citations
Above a floor, length did not matter. A labelled answer paragraph, a visible date and Article + FAQPage schema did.
Can it be fetched
If a crawler cannot reach the exact URL, or the host cannot rank in Bing, nothing else on this list matters.
Is the answer in the HTML
Most citation crawlers read the raw server response and never run JavaScript. The answer has to be in that document.
Machine-readable
Structured data and dates tell an assistant what the page is, who published it and how fresh it is.
Site hygiene
Discovery aids. Cheap to fix, low measured effect on our own sites.
Questions
What is citation readiness?
Whether an AI assistant can fetch your page, read the answer in the raw HTML without running JavaScript, understand what the page is from its structured data, and then cite it with a link. The score measures those conditions against patterns that separated cited pages from uncited ones on our own network of about 60 sites over six weeks.
Why does Bing matter for Microsoft Copilot?
Copilot citations sit downstream of Bing search ranking. On our own sites (69 verified properties), every site with zero Bing impressions had zero Copilot citations. That is a measurement on our sites, not a prediction for yours. That is why the domain and robots.txt checks for bingbot carry the highest weights.
Do I need an llms.txt file?
No measured effect. An analysis of roughly 300,000 domains found zero correlation between llms.txt and AI citations, and on our own sites the cited pages appeared zero times in their own site llms.txt. The tool reports it as information and gives it no weight.
Does blocking GPTBot hurt citations?
Not for ChatGPT search. GPTBot is the training crawler; ChatGPT search and its citations come from OAI-SearchBot, and on-demand page reads come from ChatGPT-User. Block GPTBot if you want; keep OAI-SearchBot and ChatGPT-User allowed. The tool reports each bot separately.
Is this free?
Yes. Scoring any public page is free, with no account and no email. A paid tier with a longer fix list and weekly monitoring is coming; the founding list on any report page is the way to hear about it first.
What does the bot fetch?
The exact URL you enter (following up to 5 redirects, 10 second timeout, 2 MB body cap), the same URL again with a bingbot user-agent, plus robots.txt, sitemap.xml (and up to three child sitemaps) and llms.txt on that host. Results are cached for one hour. Nothing else is stored.