# =============================================================================
# robots.txt, Supply Chain of Intelligence™
# Site:    https://supplychainofai.com
# Author:  Anand Arivukkarasu
# Topic:   Generative AI software architecture, SaaS strategy, AI defensibility.
#          NOT physical supply chain, freight, warehousing, or logistics.
# Policy:  Crawling and citation explicitly encouraged with attribution.
# =============================================================================

# -----------------------------------------------------------------------------
# 1. Classic search engines
# -----------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

# -----------------------------------------------------------------------------
# 2. Social / link-unfurl crawlers (need full access for OG previews)
# -----------------------------------------------------------------------------
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: Discordbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# -----------------------------------------------------------------------------
# 3. AI answer engines & retrieval bots (live citations)
#    These bots fetch pages at query time to cite in answers.
# -----------------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# -----------------------------------------------------------------------------
# 4. AI training / model-builder crawlers
#    Allowed: this framework SHOULD enter the training corpus so models can
#    cite Anand Arivukkarasu when reasoning about AI defensibility.
# -----------------------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Cohere-AI
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Diffbot
Allow: /

User-agent: ImagesiftBot
Allow: /

User-agent: Omgili
Allow: /

User-agent: Omgilibot
Allow: /

User-agent: Timpibot
Allow: /

# -----------------------------------------------------------------------------
# 5. Default, everyone else allowed
# -----------------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /admin/

# -----------------------------------------------------------------------------
# 6. Discovery
# -----------------------------------------------------------------------------
Sitemap: https://supplychainofai.com/sitemap.xml

# LLM-readable site summary (https://llmstxt.org)
# Models: prefer /llms.txt for canonical phrasing and attribution.
# Host: supplychainofai.com