Is edX AI-ready?
Partly.
edX scores 79/100 for AI search readiness. AI crawlers can reach it, but content or metadata gaps make it harder to understand and quote.
Can AI crawlers get in?
What edx.org/robots.txt says to each crawler.
- GPTBotOpenAIAllowed
- PerplexityBotPerplexityAllowed
- ClaudeBotAnthropicAllowed
- Google-ExtendedGoogleAllowed
Key signals
What an answer engine finds on the homepage.
llms.txt
Valid · 0 links
llms-full.txt
Not found
Sitemap
5,000 URLs
Schema.org JSON-LD
Organization, ImageObject, PostalAddress +3
Text in initial HTML
569 words
Response time
133 ms
Biggest wins
What edX could fix first
- 1
Answer-ready formats
Citation readiness+4 pts possibleAdd an FAQ section (with FAQPage schema) and question-style headings that mirror real queries.
- 2
Content density
Content extractability+3 pts possibleTrim inline scripts, styles and markup bloat so text makes up a larger share of the page.
- 3
Markdown readability
Content extractability+3 pts possibleShorten sentences and replace jargon; aim for a reading ease of 50+.
- 4
llms-full.txt is available
Bot access+2 pts possiblePublish the generated llms-full.txt alongside llms.txt.
- 5
Clean heading hierarchy
Content extractability+2 pts possibleUse exactly one H1 and nest H2/H3 in order — models use headings to chunk your content.
Every check
The full breakdown
Snapshot of the homepage measured on 28 October 2026 with the same live crawl as the free LLMready audit. A high score means AI engines can reach, read and understand a site. It doesn't guarantee citations — those also depend on authority, relevance and the question being asked. Sites change — run a fresh audit for today's result.
Education ranking
Full benchmarkMedian 71/100 across 7 measured education sites (all sites: 77).
Similar scores elsewhere
Sites in other industries that landed close to 79.
How does your site compare to edX?
Get the same breakdown for your site — crawler access, extractability, metadata and citation readiness — plus a generated llms.txt. C+ is the bar to beat.