# Texas Autopsy Services — we want to be crawled, quoted, and cited.
# Generated from src/lib/robots.ts. Edit the policy there, not here.

# Content-Signal: search=yes, ai-input=yes, ai-train=yes
# Affirmative on all three: index this content, quote it as an answer
# input, and train on it. Stated as a comment because the directive form
# is not standard and makes the file fail strict robots.txt validators.

# Everything not named below.
User-agent: *
Allow: /
Allow: /api/public/
Disallow: /api/
Disallow: /admin/
Disallow: /blog-shell/

# Retrieval crawlers — these put us in search results and AI answers.
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Google-InspectionTool
User-agent: Storebot-Google
User-agent: Bingbot
User-agent: msnbot
User-agent: DuckDuckBot
User-agent: DuckAssistBot
User-agent: Applebot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MistralAI-User
User-agent: meta-externalfetcher
User-agent: Amazonbot
Allow: /
Allow: /api/public/
Disallow: /api/
Disallow: /admin/
Disallow: /blog-shell/

# Training and model-grounding crawlers — allowed by business decision.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: CCBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Bytespider
User-agent: Diffbot
User-agent: Timpibot
User-agent: omgili
User-agent: omgilibot
Allow: /
Allow: /api/public/
Disallow: /api/
Disallow: /admin/
Disallow: /blog-shell/

# Plain-text site summary for LLM consumers: https://www.texasautopsyservices.com/llms.txt
Sitemap: https://www.texasautopsyservices.com/sitemap.xml