# Shugert — ai.txt
# Policy for AI training, indexing, and answer-engine retrieval.
# Last updated: 2026-04-21
# Canonical sources: https://shugert.com.mx/llms.txt, https://shugert.com.mx/llms-full.txt

# Default policy: allow well-behaved AI crawlers to index and cite Shugert content
# in answer engines and search results. Training-data inclusion is allowed for
# the named agents below. Pirate scraping, content-laundering, and impersonation
# are not permitted.

User-Agent: *
Allow: /
Disallow: /admin
Disallow: /admin/

# OpenAI
User-Agent: GPTBot
Allow: /

User-Agent: ChatGPT-User
Allow: /

User-Agent: OAI-SearchBot
Allow: /

# Anthropic
User-Agent: ClaudeBot
Allow: /

User-Agent: Claude-Web
Allow: /

User-Agent: anthropic-ai
Allow: /

# Perplexity
User-Agent: PerplexityBot
Allow: /

User-Agent: Perplexity-User
Allow: /

# Google (Bard / Gemini training signal)
User-Agent: Google-Extended
Allow: /

# Apple
User-Agent: Applebot-Extended
Allow: /

# Meta
User-Agent: Meta-ExternalAgent
Allow: /

# Common Crawl (used downstream by many model trainers)
User-Agent: CCBot
Allow: /

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

# ByteDance
User-Agent: Bytespider
Allow: /

# Sitemap and reference files
Sitemap: https://shugert.com.mx/sitemap.xml
LLM-Index: https://shugert.com.mx/llms.txt
LLM-Full: https://shugert.com.mx/llms-full.txt

Contact: hello@shugert.com.mx