# Managed Data Platform — crawler directives for search engines and AI providers
# https://sales.managed-data-platform.com
#
# AI / agent discovery (fetch these after robots.txt):
#   https://sales.managed-data-platform.com/llms.txt
#   https://sales.managed-data-platform.com/llms-full.txt
#   https://sales.managed-data-platform.com/ai.txt
#   https://sales.managed-data-platform.com/.well-known/llms.txt
#   https://sales.managed-data-platform.com/sitemap.xml

User-agent: *
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt
Allow: /.well-known/llms.txt
Allow: /sitemap.xml
Allow: /sitemap-pages.xml
Allow: /sitemap-data-sources.xml
Disallow: /api/

# OpenAI (ChatGPT, SearchGPT)
User-agent: GPTBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

# Google (Search + Gemini / AI training opt-in via Google-Extended)
User-agent: Googlebot
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/

# Anthropic (Claude)
User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: Claude-Web
Allow: /
Disallow: /api/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /api/

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

# Meta (Llama training / Meta AI)
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /api/

User-agent: FacebookBot
Allow: /
Disallow: /api/

# Apple (Apple Intelligence / Siri)
User-agent: Applebot
Allow: /
Disallow: /api/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

# Amazon (Alexa / AWS AI)
User-agent: Amazonbot
Allow: /
Disallow: /api/

# ByteDance / TikTok
User-agent: Bytespider
Allow: /
Disallow: /api/

# Common Crawl (feeds many AI training datasets)
User-agent: CCBot
Allow: /
Disallow: /api/

# You.com
User-agent: YouBot
Allow: /
Disallow: /api/

# Diffbot
User-agent: Diffbot
Allow: /
Disallow: /api/

# Discovery files for AI systems
# LLMs.txt: curated site overview for language models
# LLMs-full.txt: expanded content index with FAQs and product details
# ai.txt: short pointer index for agents
# Sitemap index: complete URL inventory (pages + data sources)

Sitemap: https://sales.managed-data-platform.com/sitemap.xml
Sitemap: https://sales.managed-data-platform.com/sitemap-pages.xml
Sitemap: https://sales.managed-data-platform.com/sitemap-data-sources.xml