Scan a URL
The Index › Travel › united.com
F

Unitedunited.com

28/ 100 · Agentic Usability Score
SelectiveScanned 2026-09-22 · local-node · method v0.1Edge: AkamaiNetStorage
Muse
Meta
?Untested
ChatGPT Agent
OpenAI
?Untested
Claude
Anthropic
?Untested
Comet
Perplexity
?Untested
Grok Bot
xAI
◌Not disallowed
Gemini
Google
?Untested
Manus
Manus
◌Not disallowed
Instinct
Spear Street
?Untested

Score breakdown

Five pillars. Task completion is pending until the live task runner ships; the other four are rescaled to 100.
Accessrobots.txt stance + live door test
25/40
Consent & identity pathContent-Signal, published agent policy
0/10
Machine-readable surfacellms.txt, JSON-LD, landmarks, SSR
0/25
Agent protocolsUCP, MCP, A2A, OpenAPI
0/15
Task completionlive agent run: search → cart → checkout
pending

Evidence

Generated by the scanner from this run. Every line is reproducible with the open-source probe.
  • ◐Identified agents got no response within 12 seconds while a browser user-agent got the page; treated as inconclusive
  • ✓robots.txt has no rule against any user-directed agent we test
  • ◐No Content-Signal in robots.txt
  • ◐No llms.txt
  • ◐No JSON-LD structured data on the homepage
  • ◐Missing main/nav landmarks
  • ✕Homepage is a JavaScript-only shell; no readable content without executing scripts
  • ◐No agent-protocol manifest (UCP, MCP, A2A, OpenAPI)
Identified asHTTPResult
ChatGPT-User—no response
Claude-User—no response
Perplexity-User—no response
GoogleAgent-Mariner—no response
browser (human)200normal page

What United would need to change

1Give agents a front doorProtocols · up to 12 pts

A Universal Commerce Protocol manifest for shopping, or an MCP server card for everything else. An agent that can call an API never needs to hold a customer's password.

GET /.well-known/ucp
{ "ucp": { "version": "2026-01-23",
  "services": { "dev.ucp.shopping": [{ "transport": "rest", "endpoint": "https://www.united.com/api/ucp/v1" }] },
  "capabilities": { "dev.ucp.shopping.checkout": [ … ] } } }

# or
GET /.well-known/mcp.json
{ "name": "United", "endpoint": "https://www.united.com/mcp", "transport": "streamable-http" }

2Publish llms.txtSurface · up to 8 pts

A short markdown map of what the site does, where the important pages are, and how to search or check out.

/llms.txt
# United
> One paragraph on what this site is for.
- [Products](/products): how to search and filter
- [Checkout](/checkout): steps and constraints

3Add JSON-LD structured dataSurface · up to 6 pts

schema.org Organization on the homepage, Product + Offer on product pages, with price and availability.

<script type="application/ld+json">
{ "@context": "https://schema.org", "@type": "Organization", "name": "United", "url": "https://www.united.com/" }
</script>

4Use semantic landmarksSurface · up to 5 pts

main, nav, header, footer and labeled forms. Everything an accessibility audit already asks for.

<header>…</header>
<nav aria-label="Primary">…</nav>
<main>…</main>
<form aria-label="Site search"><label for="q">Search</label><input id="q" name="q"></form>

5Server-render the pageSurface · up to 4 pts

The homepage has no readable content without executing scripts. Agents that read HTML get nothing.

# render product, price and navigation into the HTML response
# hydrate on the client afterwards

6Say your stance with a Content-SignalConsent · up to 3 pts

Two lines in robots.txt end the guessing game. ai-input covers agents reading pages on a person's behalf.

User-Agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /