# Robots.txt file for https://www.llcuniversity.com/
# Policy: AI bots that cite us and send clicks are ALLOWED. They need no rule,
# since robots.txt allows by default. Bots that only collect model training
# data are BLOCKED. Blocking a training bot does not affect that company's
# search or citation bots.
# Updated 2026-08-13.

# Global rules for all bots except the ones specified below
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-content/uploads/wpforms/
Disallow: */?scroll*
Disallow: /*/feed/
Allow: /feed/atom/

# ---------- Retrieval bots: ALLOWED ----------
# These fetch pages to answer user questions and link back to the source.
# They are allowed by default and deliberately have NO group of their own.
# A bot with its own group ignores the global rules above, so giving them an
# "Allow: /" block would exempt them from our wp-admin and wpforms blocks.
#
# OAI-SearchBot         OpenAI      surfaces us in ChatGPT search answers
# ChatGPT-User          OpenAI      live fetch when a ChatGPT user asks
# Claude-SearchBot      Anthropic   indexing for Claude citations
# Claude-User           Anthropic   live fetch when a Claude user asks
# PerplexityBot         Perplexity  indexing for Perplexity citations
# Perplexity-User       Perplexity  live fetch when a Perplexity user asks
# meta-externalfetcher  Meta        live fetch for Meta AI users
# Googlebot, Bingbot, Applebot      unchanged, standard search crawling
# Google-Extended		    controls Gemini model training and grounding

# ---------- Training-only bots: no links, no attribution, no traffic ----------

# GPTBot collects training data for OpenAI's models. Blocking it does not affect
# ChatGPT search results or citations (OAI-SearchBot and ChatGPT-User stay allowed)
User-agent: GPTBot
Disallow: /

# ClaudeBot collects training data for Anthropic's models. Blocking it does not
# affect Claude citations (Claude-SearchBot and Claude-User stay allowed)
User-agent: ClaudeBot
Disallow: /

# Retired Anthropic training agents, listed for full coverage
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Applebot-Extended controls Apple Intelligence model training only.
# Does not affect Siri or Spotlight search (regular Applebot stays allowed)
User-agent: Applebot-Extended
Disallow: /

# meta-externalagent collects training data for Meta's AI models.
# meta-externalfetcher (live user-requested fetches) is intentionally not blocked
User-agent: meta-externalagent
Disallow: /

# Amazonbot collects data for Amazon's AI products
User-agent: Amazonbot
Disallow: /

# CCBot builds the Common Crawl public dataset, which many AI companies use for training
User-agent: CCBot
Disallow: /

# Specify sitemap locations
Sitemap: https://www.llcuniversity.com/feed/atom/
Sitemap: https://www.llcuniversity.com/sitemap_index.xml