AI Search (GEO) Checker

Check whether ChatGPT, Perplexity, Claude, Copilot and Google AI Overviews can crawl, understand and cite your page, and get a prioritised list of fixes.

Try: wikipedia.org, github.com, developer.mozilla.org
C
AI search (GEO) readiness report

https://developer.mozilla.org/en-US/

Score 75/100 · Scanned 13 Oct 2026, 04:47 UTC · by WhatsMyIPNumber
Passed7
Improve10
Blocking0

AI crawler access

from robots.txt
CrawlerOperatorUsed forAccess
GooglebotGoogleSearch and AI Overviews / AI Mode Allowed
BingbotMicrosoftBing and Copilot answers Allowed
OAI-SearchBotOpenAIChatGPT search results Allowed
ChatGPT-UserOpenAIPages fetched when a ChatGPT user asks Allowed
PerplexityBotPerplexityPerplexity answer engine index Allowed
Perplexity-UserPerplexityPages fetched for a user's question Allowed
Claude-SearchBotAnthropicClaude search results Allowed
Claude-UserAnthropicPages fetched when a Claude user asks Allowed
DuckAssistBotDuckDuckGoDuckAssist answers Allowed
ApplebotAppleSiri and Spotlight suggestions Allowed
GPTBotOpenAIModel training training Allowed
ClaudeBotAnthropicModel training training Allowed
Google-ExtendedGoogleGemini training and grounding (control token) training Allowed
Applebot-ExtendedAppleApple Intelligence training (control token) training Allowed
CCBotCommon CrawlOpen web dataset used by many AI models training Allowed
Meta-ExternalAgentMetaMeta AI training training Allowed
BytespiderByteDanceModel training training Allowed
AmazonbotAmazonAlexa and Amazon AI Allowed

AI access

Googlebot and Bingbot can crawl the page
Required for Google AI Overviews / AI Mode and Microsoft Copilot.
AI answer-engine crawlers are allowed
OAI-SearchBot, PerplexityBot, Claude-SearchBot and others can fetch the page.
AI training crawlers are allowed
GPTBot, ClaudeBot, Google-Extended, CCBot and others may use the content for training.
Blocking training bots is a business decision; it does not stop AI search citations.
No llms.txt
llms.txt is a proposed standard (llmstxt.org): a Markdown summary of your site and key links for language models.
Publish /llms.txt with a short description and links to your most important pages. Support varies by AI provider.

Content

558 words of server-rendered text
Visible without JavaScript, so AI crawlers can read it.
0 H1 and 0 H2 headings
Clear sections help AI systems find and quote the right passage.
Use one H1 and descriptive H2 sections for each sub-topic.
No question-style headings
Headings phrased as questions match how people ask AI assistants.
Add headings such as 'What is …?' or 'How do I …?' followed by a direct 1–2 sentence answer.
No lists or tables
Structured facts (steps, comparisons, specs) are easy for AI engines to extract and cite.
Present steps, specs and comparisons as lists or tables.
0 outbound links to sources
Citing reputable sources supports accuracy and trust signals.
Reference primary sources, standards or data where you make factual claims.

Trust

No structured data (JSON-LD)
Schema.org markup tells machines exactly what the page is about and who published it.
Add JSON-LD for Organization plus Article, Product, FAQPage, HowTo or LocalBusiness as appropriate.
No author information
Named authors and publishers support experience and expertise signals.
Show the author and add author to your Article schema.
Content freshness
Date found: Tue, 13 Oct 2026 01:21:06 GMT
No Organization schema
Helps AI systems connect the page to your brand entity.
Add Organization schema with name, logo, url and sameAs profiles.

Technical

HTTPS
https://developer.mozilla.org/en-US/
Title or description missing
Write a descriptive title and summary; AI engines often reuse them.
No canonical URL
Add a canonical link to consolidate duplicates.
XML sitemap found
Helps crawlers discover and refresh content.
Server responded in 332 ms
Slow pages may be skipped or time out when AI tools fetch them live.

AI engines use many undisclosed ranking signals. This checker covers the technical and content factors you control; it cannot guarantee citations.

What is GEO (Generative Engine Optimization)?

More and more people get answers from AI assistants and AI-powered search, such as ChatGPT search, Perplexity, Claude, Microsoft Copilot and Google's AI Overviews and AI Mode, instead of a list of blue links. Generative Engine Optimization (GEO), also called AI search optimization or AEO, is the practice of making your content easy for these systems to access, understand and cite as a source in their answers. It builds on classic SEO: pages that rank and are crawlable in search are the raw material AI answers are made from.

What this GEO checker tests

  • AI crawler access: we read your robots.txt and check 18 crawlers individually. We separate answer-engine bots (OAI-SearchBot, PerplexityBot, Claude-SearchBot…) that fetch pages to cite them, from training bots (GPTBot, ClaudeBot, Google-Extended, CCBot…) that collect data for model training. Blocking training bots is a legitimate choice; blocking answer-engine bots or Googlebot/Bingbot removes you from AI answers.
  • llms.txt: a proposed convention for a Markdown file that summarises your site for language models.
  • Machine-readable content: how much text is in the server HTML (many AI crawlers do not execute JavaScript), heading structure, question-style headings, lists, tables and source citations.
  • Trust signals: structured data, author, organization identity and freshness, the experience-expertise-authority-trust (E-E-A-T) cues that help engines decide what to quote.
  • Technical basics: HTTPS, title and description, canonical URL, sitemap and server response time.

How to get cited by AI search engines

  1. Be crawlable: allow Googlebot, Bingbot and the AI search bots you want to appear in, and render content on the server.
  2. Answer questions directly: start sections with the question as a heading and a clear one- or two-sentence answer, then the detail.
  3. Structure facts: use lists, tables, definitions and step-by-step instructions that can be lifted accurately.
  4. Show expertise: name the author, add credentials, cite primary sources and keep pages updated with visible dates.
  5. Mark it up: add schema.org JSON-LD for your Organization and for Articles, Products, FAQs or HowTos.
  6. Build authority: AI engines favour sources that are well-linked and mentioned across the web, just as search engines do.

Complement this report with the SEO checker, the website speed test and the security scanner.

Example llms.txt

# Example Co

> Example Co makes accounting software for small businesses in the UK.

## Docs
- [Getting started](https://example.com/docs/start): set up your account
- [Pricing](https://example.com/pricing): plans and VAT

## Optional
- [Blog](https://example.com/blog)

Frequently asked questions

Is GEO different from SEO?

It extends it. The foundations (crawlability, quality content, authority, structured data) are the same. GEO puts extra weight on clear, quotable answers, on server-rendered content and on access for AI crawlers.

Should I block GPTBot and other AI crawlers?

Blocking training crawlers keeps your content out of future model training but does not stop AI search engines from citing you, as long as their search bots and Googlebot/Bingbot are allowed. Decide based on your business model.

Do AI engines use llms.txt?

Support is still emerging and varies by provider. It is cheap to add and can help tools that look for it, but it is not a replacement for good, crawlable pages.

Copied to clipboard