{
  "study": {
    "title": "BORVIS public agency website discovery study",
    "checked_date": "2026-09-01",
    "sample_type": "Purposive sample of active branding, design, creative and web agencies previously qualified through public commercial-activity research; not a random or representative industry sample.",
    "sample_size": 48,
    "cohort_sizes": {
      "India": 30,
      "International": 18
    }
  },
  "response_quality": {
    "homepage_http_200": {
      "numerator": 45,
      "denominator": 48,
      "percent": 93.8
    },
    "homepage_not_200_or_timed_out": {
      "numerator": 3,
      "denominator": 48,
      "percent": 6.2
    },
    "valid_robots_file": {
      "numerator": 44,
      "denominator": 48,
      "percent": 91.7
    },
    "valid_xml_sitemap": {
      "numerator": 44,
      "denominator": 48,
      "percent": 91.7
    }
  },
  "llms_txt": {
    "valid_minimum_format_overall": {
      "numerator": 18,
      "denominator": 48,
      "percent": 37.5
    },
    "valid_minimum_format_india": {
      "numerator": 16,
      "denominator": 30,
      "percent": 53.3
    },
    "valid_minimum_format_international": {
      "numerator": 2,
      "denominator": 18,
      "percent": 11.1
    },
    "median_word_count": 585.5,
    "word_count_min": 191,
    "word_count_max": 8745,
    "with_blockquote_summary": {
      "numerator": 16,
      "denominator": 18,
      "percent": 88.9
    },
    "with_markdown_links": {
      "numerator": 17,
      "denominator": 18,
      "percent": 94.4
    },
    "with_optional_section": {
      "numerator": 2,
      "denominator": 18,
      "percent": 11.1
    },
    "with_llms_full_txt_link": {
      "numerator": 0,
      "denominator": 18,
      "percent": 0.0
    }
  },
  "crawler_controls": {
    "denominator": "44 sites with a valid robots.txt response",
    "oai_searchbot_explicit_disallow_all": {
      "numerator": 0,
      "denominator": 44,
      "percent": 0.0
    },
    "oai_searchbot_explicit_allow_root": {
      "numerator": 4,
      "denominator": 44,
      "percent": 9.1
    },
    "oai_searchbot_wildcard_not_blocked_at_root": {
      "numerator": 40,
      "denominator": 44,
      "percent": 90.9
    },
    "gptbot_explicit_disallow_all": {
      "numerator": 4,
      "denominator": 44,
      "percent": 9.1
    }
  },
  "homepage_observations": {
    "denominator": "45 homepages returning HTTP 200; route detection uses homepage links and can miss JavaScript-only or differently named routes.",
    "self_canonical": {
      "numerator": 34,
      "denominator": 45,
      "percent": 75.6
    },
    "non_self_canonical": {
      "numerator": 7,
      "denominator": 45,
      "percent": 15.6
    },
    "no_canonical_detected": {
      "numerator": 4,
      "denominator": 45,
      "percent": 8.9
    },
    "entity_schema_detected": {
      "numerator": 30,
      "denominator": 45,
      "percent": 66.7
    },
    "zero_h1": {
      "numerator": 7,
      "denominator": 45,
      "percent": 15.6
    },
    "one_h1": {
      "numerator": 30,
      "denominator": 45,
      "percent": 66.7
    },
    "multiple_h1": {
      "numerator": 8,
      "denominator": 45,
      "percent": 17.8
    },
    "service_route_link_detected": {
      "numerator": 27,
      "denominator": 45,
      "percent": 60.0
    },
    "work_route_link_detected": {
      "numerator": 41,
      "denominator": 45,
      "percent": 91.1
    },
    "about_route_link_detected": {
      "numerator": 28,
      "denominator": 45,
      "percent": 62.2
    },
    "insight_route_link_detected": {
      "numerator": 30,
      "denominator": 45,
      "percent": 66.7
    }
  },
  "interpretation_limits": [
    "Presence of llms.txt is an adoption observation, not evidence of indexing, ranking, citation, recommendation or traffic impact.",
    "The India/international cohort difference may reflect sample selection, platform/vendor adoption, timing or other confounders; no causal explanation was tested.",
    "A robots.txt rule indicates a published access preference; it does not prove that a platform crawled, indexed or used the site.",
    "Schema, canonical and route fields are homepage-source observations, not full technical audits.",
    "HTTP results are a time-stamped snapshot and can change."
  ]
}
