# =====================================================================
# robots.txt — coffeestrategies.com
# =====================================================================

# ---------------------------------------------------------------------
# Content usage signals  (see contentsignals.org — policy is CC0)
# As a condition of accessing this site, crawlers agree to the signals
# below. "yes" permits the use; "no" does not. These express a
# reservation of rights; they are preferences, not an access control.
#   search   — index the content and link back to it in results
#   ai-input — use the content to generate real-time AI answers (e.g. RAG)
#   ai-train — use the content to train or fine-tune AI models
# ---------------------------------------------------------------------

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ---------------------------------------------------------------------
# AI answer / search crawlers are intentionally NOT listed separately.
# They inherit the group above (allowed to crawl, and they read the
# Content-Signal line). Shown here only for reference:
#   OAI-SearchBot, ChatGPT-User   (OpenAI / ChatGPT)
#   Claude-SearchBot, Claude-User (Anthropic / Claude)
#   PerplexityBot                 (Perplexity)
#   Googlebot, Applebot, Bingbot  (search + their AI answer surfaces)
# ---------------------------------------------------------------------

# ---------------------------------------------------------------------
# AI *training* crawlers — opt out (matches ai-train=no above).
# These collect training data and don't drive citations, so blocking
# them costs no discoverability.
# ---------------------------------------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# ---------------------------------------------------------------------
# Optional, stronger training opt-out. Each of these ALSO trims some
# AI-answer visibility, so they're commented out by default. Uncomment
# any you want to enforce:
#   Google-Extended    — opts out of Google Gemini training/grounding
#                        (does NOT affect Google Search or AI Overviews),
#                        but may reduce presence in Gemini app answers.
#   meta-externalagent — Meta AI training.
#   Bytespider         — ByteDance/TikTok; often ignores robots.txt anyway.
# ---------------------------------------------------------------------
# User-agent: Google-Extended
# Disallow: /
#
# User-agent: meta-externalagent
# Disallow: /
#
# User-agent: Bytespider
# Disallow: /

Sitemap: https://coffeestrategies.com/sitemap_index.xml