# Content-Signal declares how this site's content may be used after access.
# See https://contentsignals.org for the vocabulary.
# This site declares: search=yes, ai-input=yes, ai-train=no

User-Agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /api/
Disallow: /api/admin/
Disallow: /api/cron/
Disallow: /private/
Disallow: /search?*
Disallow: /search/*?*
Disallow: /*/search?*
Disallow: /*/search/*?*
Disallow: /account
Disallow: /*/account
Disallow: /login
Disallow: /*/login
Disallow: /register
Disallow: /*/register
Disallow: /forgot-password
Disallow: /*/forgot-password
Disallow: /design-system
Disallow: /*/design-system
Disallow: /test/homepage
Disallow: /*/test/homepage

User-Agent: Googlebot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /api/
Disallow: /api/admin/
Disallow: /api/cron/
Disallow: /private/
Disallow: /search?*
Disallow: /search/*?*
Disallow: /*/search?*
Disallow: /*/search/*?*
Disallow: /account
Disallow: /*/account
Disallow: /login
Disallow: /*/login
Disallow: /register
Disallow: /*/register
Disallow: /forgot-password
Disallow: /*/forgot-password
Disallow: /design-system
Disallow: /*/design-system
Disallow: /test/homepage
Disallow: /*/test/homepage

User-Agent: Googlebot-Image
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /api/
Disallow: /api/admin/
Disallow: /api/cron/
Disallow: /private/
Disallow: /search?*
Disallow: /search/*?*
Disallow: /*/search?*
Disallow: /*/search/*?*
Disallow: /account
Disallow: /*/account
Disallow: /login
Disallow: /*/login
Disallow: /register
Disallow: /*/register
Disallow: /forgot-password
Disallow: /*/forgot-password
Disallow: /design-system
Disallow: /*/design-system
Disallow: /test/homepage
Disallow: /*/test/homepage

# OpenAI - appear in ChatGPT
User-Agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# ChatGPT real-time browsing
User-Agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# OpenAI - ChatGPT search results
User-Agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Anthropic - appear in Claude
User-Agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Anthropic - Claude search results
User-Agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Claude real-time browsing on a user's request
User-Agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Anthropic - appear in Claude
User-Agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Claude real-time browsing
User-Agent: Claude-Web
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Perplexity AI search
User-Agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Perplexity real-time browsing on a user's request
User-Agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Google AI features
User-Agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Alexa/Amazon services
User-Agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Apple AI features
User-Agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Link previews (sharing)
User-Agent: facebookexternalhit
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account

# Meta AI training - caused 28x bandwidth spike
User-Agent: meta-externalagent
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account
Crawl-delay: 15

# Meta AI crawler
User-Agent: FacebookBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account
Crawl-delay: 15

# Common Crawl - just training data scraping
User-Agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account
Crawl-delay: 30

# TikTok/ByteDance - known aggressive
User-Agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account
Crawl-delay: 30

# Cohere AI
User-Agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /_next/
Disallow: /account
Disallow: /*/account
Crawl-delay: 15

# Rate limit aggressive SEO crawler (198 requests in 30 mins)
User-Agent: MJ12bot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /api/
Disallow: /private/
Crawl-delay: 10

# llms.txt: https://www.saltoftheearthnatural.com/llms.txt
Host: https://www.saltoftheearthnatural.com
Sitemap: https://www.saltoftheearthnatural.com/sitemap.xml