# Ibex Insights: https://www.ibexinsights.co
# AI-Powered Research, Traditional & Generative Search Optimization,
# Marketing, and AI Agents for Education Institutions.
#
# We welcome AI search and answer engines. Indexing our content is how
# higher-ed leaders find our work.

User-agent: *
Allow: /
Disallow: /demo-engine.js
# Build-time ETL source/notes are not content, also 404'd at the edge.
Disallow: /data/etl/

# ----------------------------------------------------------------------
# Traditional search engines
# ----------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# ----------------------------------------------------------------------
# AI / answer-engine crawlers (allow-listed for citation)
# ----------------------------------------------------------------------

# OpenAI: training, browsing, search index
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Google: Gemini / AI Overview retrieval-augmented generation
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Anthropic: Claude search & answer
User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

User-agent: Cohere-AI
Allow: /

# Meta AI / Facebook share-card fetcher
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Amazon, Mistral, You, Phind, Brave, Diffbot
User-agent: Amazonbot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: YouBot
Allow: /

User-agent: PhindBot
Allow: /

User-agent: Bravebot
Allow: /

User-agent: Diffbot
Allow: /

# ByteDance / TikTok / Doubao
User-agent: Bytespider
Allow: /

User-agent: TikTokSpider
Allow: /

# Common Crawl (training corpus)
User-agent: CCBot
Allow: /

# Timpi (independent search)
User-agent: Timpibot
Allow: /

# ----------------------------------------------------------------------
# Sitemaps
# ----------------------------------------------------------------------
# /sitemap.xml is now a sitemap INDEX that recurses into all children below.
# The children are also listed explicitly for crawlers that don't recurse indexes.
Sitemap: https://www.ibexinsights.co/sitemap.xml
Sitemap: https://www.ibexinsights.co/sitemap-pages.xml
Sitemap: https://www.ibexinsights.co/data/sitemap-data.xml
Sitemap: https://www.ibexinsights.co/data/sitemap-rankings.xml
Sitemap: https://www.ibexinsights.co/data/sitemap-states.xml
Sitemap: https://www.ibexinsights.co/data/sitemap-fields.xml
Sitemap: https://www.ibexinsights.co/data/sitemap-bucketb.xml

# ----------------------------------------------------------------------
# LLM-readable site descriptions (the "robots.txt for the AI era")
# https://www.ibexinsights.co/llms.txt        – short index
# https://www.ibexinsights.co/llms-full.txt   – full content map
# ----------------------------------------------------------------------