Agent Web Index › nema.org
Can AI assistants read nema.org?
Measured on 2026-09-19 by asking the site six times — once as a browser, once as each of the five crawlers that feed ChatGPT, Claude, Perplexity and Gemini — and comparing what came back.
D59 / 100
2 of 7 assistants can read this page.
More readable than 52% of the 44,380 sites measured so far.
Structured data: WebPage.
What each crawler got back
| Crawler | HTTP | Result | robots.txt |
|---|---|---|---|
| ClaudeBot (Claude) | 404 | error | no-rule |
| GPTBot (ChatGPT) | 404 | error | blocked |
| OAI-SearchBot (ChatGPT Search) | 404 | error | no-rule |
| PerplexityBot (Perplexity) | 404 | error | no-rule |
| Google-Extended (Gemini, AI Overviews) | 200 | can read it | no-rule |
| meta-externalagent | 200 | can read it | no-rule |
| amazonbot | 404 | error | no-rule |
The checks
- Answers AI agents like it answers people29%
- Readable without JavaScript100%
- robots.txt lets the crawlers in86%
- Facts in JSON-LD67%
- Content reachable, not buried60%
- Publishes a map of itself0%
- Plain structure57%
Embed this score
Put the badge on nema.org — it links back here, and re-measures every time this index re-crawls.
<a href="https://shop.lumnika.com/ai-readiness/nema.org"><img src="https://shop.lumnika.com/ai-readiness/nema.org/badge.svg" alt="AI readability"></a>
Method. Six live HTTP requests plus robots.txt, llms.txt, sitemap.xml and security.txt, 12-second timeout each,
from a single vantage point. Blocking AI crawlers is a legitimate choice, not a failure: this page records what is true, not what should be.
Domain comes from a shop-platform seed (Shopify/WooCommerce/Magento/BigCommerce/Shopline fingerprint or JSON-LD price), not the Tranco traffic ranking. One page per domain — the homepage — is audited.
Part of the Agent Web Index, 44,380 domains measured, updated continuously.
Part of the Agent Web Index, 44,380 domains measured, updated continuously.