amazon.com
This site is essentially invisible to AI agents.
Needs work (11)
GET /agents.md returned 404
agents.md is the primary self-description file AI agents look for when deciding how to interact with a site.
GET /llms.txt returned 404
llms.txt is the emerging convention for pointing LLMs at the most relevant content on a site.
GET /llms-full.txt returned 404
llms-full.txt provides an extended, unabridged version of llms.txt for agents that can handle more context.
homepage ignores Accept: text/markdown (content-type: text/html;charset=UTF-8)
Agents that request text/markdown should receive a lightweight markdown response instead of full HTML.
no JSON-LD structured data found on homepage
JSON-LD structured data gives agents a machine-readable summary of what an organization or page is.
no sitemap found at /sitemap.xml or referenced in robots.txt
A sitemap helps agents discover the full set of pages worth crawling or indexing.
GET /.well-known/mcp.json returned 404
An MCP server card at a well-known location lets agents discover tool/action interfaces automatically.
GET /.well-known/verified.md returned 404
Publishing /.well-known/verified.md is the strongest first-party signal that a site actively participates in agent-readiness self-attestation.
no x402 signals detected (probed /api paths, headers, agents.md)
x402 is an emerging standard for agent-native micropayments over HTTP 402. Early support signals forward-looking infrastructure.
homepage missing: OG tags
Title, meta description, and Open Graph tags give agents (and the humans they act for) a reliable summary of the page.
text-to-markup ratio 0.7% (threshold 2%)
If the homepage is almost entirely markup/script with little extractable text, agents that don't execute JS see an empty page.
Passed (3)
robots.txt does not block crawlers; explicit directives for GPTBot, ClaudeBot, PerplexityBot, Google-Extended
robots.txt controls whether AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended) can access your site at all.
HTTPS reachable and HTTP redirects to HTTPS
Agents should reach the site over HTTPS, and plain HTTP should redirect there so credentials and payloads are never sent in the clear.
homepage accessible to scanner user agent
If the homepage returns a 403 or a challenge page to a scanner-style user agent, real agents likely get blocked too.
What this means for amazon.com
- AI assistants answering questions in your category cannot read how amazon.com wants to be used, so they cite competitors who declare themselves.
- Assistants that look for a plain-language summary of amazon.com find nothing, so what they say about you is guesswork assembled from third-party pages.
- Agents that want your full content in one clean file have to crawl page by page instead, and most give up early.
- Agents that ask for a clean text version of your pages get raw HTML instead, burning their limited attention on your navigation and scripts.
- Agents cannot reliably extract what amazon.com offers, so they describe you vaguely or not at all.
- Crawlers have no map of amazon.com, so new pages surface late or never.
- Agents can read amazon.com but cannot interact with it. To them you are a brochure, not a service.
- Nothing proves amazon.com is who it says it is, so an agent has no way to tell you apart from an impersonator.
- Agents that can pay for content and services have no way to pay you.
- Assistants describing amazon.com rely on your titles and descriptions. Right now those are missing or malformed, so they improvise.
- Key content on amazon.com only appears after JavaScript runs. Most agents do not run it. To them those pages are blank.
Make amazon.com agent ready
Displace implements every failing check above and re-verifies monthly. Beta rate EUR 990 flat (list EUR 1,900), first 10 sites only, includes the first 3 months of certification.
Or email hello@verified.md.