Search & AI discoverability observations

{
  "schema_version": 1,
  "mode": "observational",
  "input_url": "https://example.org/",
  "collected_at": "2026-11-01T00:00:00Z",
  "limits": {
    "resources": 3,
    "http_requests": 12,
    "redirects_per_resource": 3,
    "body_bytes_per_response": 1048576,
    "dns_wait_seconds": 5,
    "request_budget_seconds": 5,
    "internal_link_sample": 20
  },
  "scope": "One page, its origin robots.txt, and at most one same-origin sitemap candidate. Redirects bounded to three per resource.",
  "interpretation": "HTTP success, directives and markup do not establish indexing, ranking, AI retrieval or citations.",
  "page": {
    "url": "https://example.org/",
    "status": 200,
    "redirect_chain": [
      {
        "url": "https://example.org/",
        "status": 200
      }
    ],
    "headers": {
      "content-type": "text/html; charset=utf-8",
      "x-robots-tag": "max-snippet:160"
    },
    "meta_robots": [
      "index,follow"
    ],
    "canonicals": [
      {
        "declared": "https://example.org/",
        "resolved": "https://example.org/",
        "valid_http_url": true
      }
    ],
    "internal_links": [
      "https://example.org/about",
      "https://example.org/evidence"
    ],
    "json_ld_blocks": 1,
    "json_ld_invalid_blocks": 0,
    "json_ld_types": [
      "Organization"
    ],
    "analysis": "HTML observations only",
    "base_element_handling": "Links resolve against final page URL; HTML base elements are not applied."
  },
  "robots": {
    "url": "https://example.org/robots.txt",
    "status": 200,
    "redirect_chain": [
      {
        "url": "https://example.org/robots.txt",
        "status": 200
      }
    ],
    "headers": {
      "content-type": "text/plain"
    },
    "availability": "available",
    "groups": [
      {
        "user_agents": [
          "*"
        ],
        "rules": [
          {
            "directive": "disallow",
            "value": "/internal/"
          }
        ]
      },
      {
        "user_agents": [
          "ExampleResearchBot"
        ],
        "rules": [
          {
            "directive": "disallow",
            "value": "/"
          }
        ]
      }
    ],
    "directives": [
      {
        "directive": "user-agent",
        "value": "*"
      },
      {
        "directive": "disallow",
        "value": "/internal/"
      },
      {
        "directive": "user-agent",
        "value": "ExampleResearchBot"
      },
      {
        "directive": "disallow",
        "value": "/"
      },
      {
        "directive": "sitemap",
        "value": "https://example.org/sitemap.xml"
      }
    ],
    "sitemaps": [
      "https://example.org/sitemap.xml"
    ],
    "interpretation": "Manual review required; no engine-specific allow/deny decision is calculated."
  },
  "sitemap": {
    "url": "https://example.org/sitemap.xml",
    "status": 200,
    "redirect_chain": [
      {
        "url": "https://example.org/sitemap.xml",
        "status": 200
      }
    ],
    "headers": {
      "content-type": "application/xml"
    },
    "note": "Response observed only; XML validity, listed URLs and sitemap index children are not evaluated."
  },
  "transport": "synthetic offline fixture"
}