Skip to content
GEO/AEO Scanner

Cette page existe en français.

GEO AUDIT · AI VISIBILITY AND ACCESSIBILITY

GEO audit: get your site cited by AI assistants

A 12-dimension diagnosis, ready-to-apply fixes and ready-to-integrate files. Then the proof, measured in ChatGPT, Claude, Gemini, Perplexity and Mistral.

Start for freeSee what you get
Results in under 30 sNo credit cardDownloadable PDF report
Real audit

geoaeoscanner.com

GEO96/100

  • 100Accessibility
  • 100Security
  • 100AI agents

Our own site, 1 November 2026 · engine 2.2.0

  • 17 AI crawlers checked in robots.txt (OpenAI, Anthropic, Perplexity, Google, Apple, Mistral…)
  • 12 dimensions scored by deterministic rules
  • 20 WCAG 2.2 A/AA accessibility rules checked
  • < 30 s for an audit without AI analysis
WHAT YOU GET

More than a score: everything you need to get cited

Every audit delivers the diagnosis, the fixes and the files to put on your site. It then measures the result in AI assistants. The excerpts shown come from a real report of our site.

  1. 12-dimension diagnosis

    AI crawler access, structured data, citability, direct answers, trust, performance and WCAG 2.2 accessibility. Every check is a published rule: the same site gets the same score.

    Real excerpt

    82 checks · 3 to fix · GEO score 96/100

    Free3 analyses per month

  2. Action plan and ready-to-apply fixes

    Actions are ranked by expected score gain. For every failed check, the exact code and where it goes, built from your site’s own data.

    Real excerpt

    Complete identity (name, url, logo, sameAs)

    "@type": "Organization",
"name": "GEO/AEO Scanner",
"url": "https://geoaeoscanner.com/",
    Freethe first 5 actionsEssentialevery action and its fix

  3. Ready-to-integrate files

    robots.txt, llms.txt, Organization and FAQ JSON-LD, security headers, security.txt, accessibility statement. Each file says whether to add it, whether it replaces or completes what you have, or whether your site is already compliant. You never get less than you already have.

    Real excerpt

    • robots.txtalready compliant
    • llms.txtalready compliant
    • schema-organization.htmlalready compliant
    • schema-faq.htmlalready compliant
    Essentialevery file

  4. Real measurement in AI assistants

    Your customers’ questions are asked to ChatGPT, Claude, Gemini, Perplexity and Mistral, with web search. You see whether you are cited, in which position and with which sources. You also see which competitors are named instead.

    Essential1 measurement per monthPro8 measurements per month

  5. Monitoring and alerts

    The scanner re-checks your pages automatically. It alerts you, in the app and by email, when the score falls below your threshold, drops sharply or can no longer be computed.

    Free1 site, monthlyEssentialweeklyProdaily monitoring

  6. API and MCP connectors

    Two different uses. The platform’s MCP connector runs and reads your audits from Claude Code, Cursor or Codex. The MCP server generated for your site lets AI assistants query it. The REST API and the WordPress plugin complete the set.

    ProAPI key and connectors

Compare plans →

COMMON ISSUES

6 issues that stop AI from reading or citing a site

Six issues the scanner detects in the HTML served to bots, each with its fix.

  1. AI crawlers blocked

    Critical impact

    If robots.txt blocks GPTBot, ClaudeBot or PerplexityBot, these assistants cannot read your pages. The scanner checks 17 AI crawlers per RFC 9309.

  2. No llms.txt file

    Medium impact

    llms.txt (llmstxt.org, a proposed standard) summarises your site and lists your key pages for language models. The scanner checks and generates it.

  3. Missing or incomplete structured data

    High impact

    Without Organization, WebSite or Product JSON-LD, AI has to guess who you are and what you offer. The report generates these blocks from your site.

  4. No direct answers

    High impact

    Assistants quote short answers to precise questions. Without a marked-up FAQ or question headings, your content is harder to cite.

  5. Content that is hard to quote

    High impact

    Passages that depend on context, no figures or sources, no definitions: the scanner measures the citability of every audited page.

  6. Inconsistent sharing metadata

    Medium impact

    Missing or conflicting meta description, Open Graph, X card and official profiles (sameAs): the scanner compares these signals.

THE 12 DIMENSIONS

The 12 dimensions we measure

Each dimension has a fixed, published weight; each check is a deterministic rule: the same site gets the same score.

The scanner fetches the HTML served to bots, reads robots.txt, llms.txt and the sitemap, explores up to 3 key pages and scores each dimension.

  • robots.txt analysis for 17 AI crawlers (RFC 9309)
  • llms.txt check and generation
  • Audit of JSON-LD, @graph and microdata
  • Citability, direct answers and trust signals (E-E-A-T)
  • Weighted overall score from deterministic, tested rules
Run an audit →
Real scores of geoaeoscanner.com (GEO score 96/100), audited on 1 November 2026.

AI crawler access

14%

robots.txt evaluated per RFC 9309 for 17 AI crawlers (OpenAI, Anthropic, Perplexity, Google, Apple, Mistral…), meta robots tag and X-Robots-Tag header.

Weight in the score: 14%

Discovery signals

9%

XML sitemap (including indexes), lastmod freshness, canonical URL, internal linking and broken outbound links on a sample.

Weight in the score: 9%

Content structure

13%

Single H1, heading hierarchy, semantic HTML5, lists and tables, text volume and readability (Flesch for English, Kandel-Moles for French).

Weight in the score: 13%

AI citability

10%

Self-contained passages, quantified facts, sources and authority links, definitions: what AI can quote verbatim.

Weight in the score: 10%

Structured data

9%

JSON-LD (including @graph) and microdata: entity identity, content type, WebSite, breadcrumbs, Product and reviews for shops.

Weight in the score: 9%

AI guide (llms.txt)

5%

Presence and quality of llms.txt in the llmstxt.org format (a proposed standard): title, summary, sections and links to key pages. It serves AI assistants and agents that read your site; Google does not state that it uses it to rank search results.

Weight in the score: 5%

Product data

8%

Online shops only (detected automatically): price, availability, identifiers and consistency between the page and Schema.

Weight in the score: 8%

Direct answers (AEO)

9%

Marked-up FAQ, question headings followed by a short answer, comparison tables and numbered steps.

Weight in the score: 9%

Trust (E-E-A-T)

5%

HTTPS, identified entity, legal notice, privacy, contact and about page, authors, dates and reviews.

Weight in the score: 5%

Performance

4%

Server response time, compression, HTML weight, caching, mobile viewport, modern image formats, blocking scripts, HSTS.

Weight in the score: 4%

Cross-platform consistency

4%

Meta description, Open Graph, X (Twitter) card, title consistency and linked official profiles (sameAs).

Weight in the score: 4%

Accessibility (WCAG / EAA)

10%

20 WCAG 2.2 A/AA rules checked on the page code (alternatives, forms, accessible names, zoom, ARIA…) and the statement required by the European Accessibility Act.

Weight in the score: 10%

The checks are based on public specifications: RFC 9309 (robots.txt), Schema.org, llmstxt.org, WCAG 2.2.

Real report

geoaeoscanner.com

1 November 2026 · engine 2.2.0 · 4 pages read

96/100

3 checks out of 82 do not pass:

  • Complete identity (name, url, logo, sameAs) · Missing: sameAs
  • Reviews or client references · None
  • Official profiles linked (>= 2) · 0 social link(s), 0 sameAs

Fix provided: Complete identity (name, url, logo, sameAs)

Inside the page <head>

<!-- To add when available (left out because unknown): sameAs -->
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "@id": "https://geoaeoscanner.com/#organization",
  "name": "GEO/AEO Scanner",
  "url": "https://geoaeoscanner.com/",
  "logo": "https://geoaeoscanner.com/favicon.svg",
  "description": "Audit de visibilité IA et d’accessibilité : 12 dimensions, 17 robots IA, 20 règles WCAG 2.2, plan d’action priorisé et fichiers prêts à intégrer.",
  "contactPoint": {
    "@type": "ContactPoint",
    "contactType": "customer support",
    "url": "https://geoaeoscanner.com/contact",
    "availableLanguage": [
      "fr",
      "en"
    ]
  }
}
</script>

Ready-to-integrate files:

  • robots.txtalready compliant
  • llms.txtalready compliant
  • schema-organization.htmlalready compliant
  • schema-faq.htmlalready compliant
  • security-headers.txtalready compliant
  • security.txtalready compliant
A REAL EXCERPT

A real report, not a mock-up

This is the audit of our own site, made by the same engine as yours. It shows what does not pass, the fix provided and the state of every file.

  • Overall score and accessibility score
  • Detail of the 12 dimensions and every check
  • Priority actions ranked by expected score gain
  • Ready-to-apply fixes and ready-to-integrate files (paid plans)
  • PDF and CSV export, time-limited share link
See what a report contains →
REAL MEASUREMENT

Proof in AI assistants, not an estimate

The scanner asks your customers’ questions to the assistants, through their API and with web search. It then analyses every answer: you see what a customer actually reads.

  • How often your brand is mentioned, per assistant and per question
  • Your pages cited as sources, and the most cited domains
  • Your average position when the assistant recommends a list
  • The competitors named and their share of voice
  • The tone of the answers that talk about you
  • Questions suggested from your site, editable before sending

Assistant answers vary from one query to the next: each measurement is a dated snapshot, to compare over time. No result is guaranteed.

One measurement

6questions at most

5AI assistants

30answers analysed

  • Perplexity
  • ChatGPT
  • Gemini
  • Claude
  • Mistral

Essential: 1 measurement per month. Pro: 8 measurements per month.

See the plans →

HOW IT WORKS

3 steps to AI visibility

01

Enter your URL

Create a free account and paste a page address. The scanner reads it like an AI crawler and scores the 12 dimensions.

02

Get your audit

In 5 to 30 seconds: scores, issues and actions ranked by expected gain. Allow 1 to 2 minutes with AI analysis (paid plans).

03

Fix and measure

Apply the fixes, integrate the files, then re-run the audit or turn on monitoring to see your scores change.

Frequently asked questions

What are GEO and AEO?

GEO refers to making a site readable and quotable by AI assistants such as ChatGPT, Claude, Gemini or Perplexity (Generative Engine Optimization). AEO refers to optimising for answer engines (Answer Engine Optimization): clear questions followed by short answers these assistants can reuse.

What exactly does the scanner check?

It fetches the HTML served to bots (without running JavaScript, like most AI crawlers), reads robots.txt for 17 AI crawlers, llms.txt and the sitemap, explores up to 3 key pages and scores 12 dimensions, including 20 WCAG 2.2 accessibility rules.

What is free?

3 analyses per month without a credit card: 12-dimension score, accessibility, AI-agent score, the first 5 actions (without fixes) and one site monitored monthly. Paid plans add fixes, AI, visibility measurement, the real browser, site crawls and the API.

Does a good score guarantee being cited by AI?

No. The score measures whether your site is accessible, understandable and quotable. Whether to cite a source is up to each assistant and also depends on the question asked and the other sources available.

All questions →

Check what AI sees of your site

Free audit

3 analyses per month, no credit card. Results in under 30 seconds.

Start for freePricing