Can AI assistants read lavenir.net?

Measured on 2026-09-19 by asking the site 5 times — once as a browser, once as each of the 4 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

What to change, in order

1. 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.
2. Mark the content with <main>
   The content-reachability check scores 1/100: with no <main> or <article> landmark, or with most of the page outside it, an assistant reads the navigation and the footer at the same cost as the text it came for.
3. 4 crawlers are named and refused in robots.txt — a deliberate choice
   ClaudeBot, GPTBot, OAI-SearchBot, PerplexityBot are blocked by a rule that names them. Nothing to fix here: this page records what is true, not what should be. It is listed so the deliberate part of the block is not confused with the accidental part above.

Get told if this changes

One email only when a measured crawler flips on lavenir.net, served to refused or back. No schedule, no newsletter; double opt-in, one-click stop.

The checks

• Answers AI agents like it answers people100%
• Readable without JavaScript100%
• robots.txt lets the crawlers in0%
• Facts in JSON-LD100%
• Content reachable, not buried1%
• Publishes a map of itself45%
• Plain structure99%

History

2026-09-18: 70 · 2026-09-19: 70

Sites with a similar score

Browse the whole index →

Embed this score

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

<a href="https://aivis.lumnika.com/ai-readiness/lavenir.net"><img src="https://aivis.lumnika.com/ai-readiness/lavenir.net/badge.svg" alt="AI readability"></a>