Can AI assistants read octopusenergy.it?

Measured on 2026-09-19 by asking the site 7 times — once as a browser, once as each of the 6 crawlers that feed ChatGPT, Claude, Perplexity, Gemini, Meta AI, Apple Intelligence and Doubao — and comparing what came back. The AI-training opt-out tokens that never crawl are read from robots.txt instead.

What each crawler got back

Vercel answers for this domain. Where a crawler above is refused while robots.txt allows it, the rule is applied by that edge, not written by the site — see how often each edge does this.

What to change, in order

1. Let in the 6 crawlers your own robots.txt already allows+6 crawlers
   ClaudeBot, GPTBot, OAI-SearchBot, PerplexityBot, Meta-ExternalAgent, Amazonbot are turned away before reading the page (served a bot challenge instead of the page), while robots.txt permits them — so this block is not written in your site. Vercel answers for this domain. Look for the bot or user-agent rules in its dashboard: that is where the decision is made, not in robots.txt. Fixing it takes this domain from 0 to 6 of 6 crawlers.
2. Publish llms.txt
   llms.txt is missing, so an assistant has to discover the site by following links. llms.txt is the emerging convention for telling an assistant which pages actually matter.

The checks

• Answers AI agents like it answers people0%
• Readable without JavaScript100%
• robots.txt lets the crawlers in100%
• Facts in JSON-LD67%
• Content reachable, not buried61%
• Publishes a map of itself45%
• Plain structure68%

Sites with a similar score

Browse the whole index →

Embed this score

Put the badge on octopusenergy.it — it links back here, and re-measures every time this index re-crawls.

<a href="https://shop.lumnika.com/ai-readiness/octopusenergy.it"><img src="https://shop.lumnika.com/ai-readiness/octopusenergy.it/badge.svg" alt="AI readability"></a>