# robots.txt for VerifyJobs.org
# Grants access to all AI and search engine crawlers

# AI crawlers - allow full access to knowledge base
User-agent: *
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt
Allow: /ai-sitemap.xml
Disallow: /logs/
Disallow: /private/
Crawl-delay: 1

# Google Search (including AI Overviews)
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Google-Extended
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt

# OpenAI GPTBot (powers ChatGPT)
User-agent: GPTBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt
Crawl-delay: 2

# Anthropic Claude
User-agent: ClaudeBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt
Crawl-delay: 2

# Perplexity AI
User-agent: PerplexityBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Crawl-delay: 2

# Bing (includes AI features)
User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: MicrosoftPreviews
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /
Crawl-delay: 2

# Apple (Siri, Spotlight)
User-agent: Applebot
Allow: /
Crawl-delay: 2

# Yandex
User-agent: YandexBot
Allow: /
Crawl-delay: 2

# Baidu
User-agent: Baiduspider
Allow: /
Crawl-delay: 2

# SEO audit bots
User-agent: AhrefsBot
Allow: /
Crawl-delay: 2

User-agent: SemrushBot
Allow: /
Crawl-delay: 2

User-agent: MJ12bot
Allow: /
Crawl-delay: 2

# AI crawler permissions - see /ai.txt for detailed policy
# AI knowledge base at /llms.txt and /llms-full.txt

# Sitemaps
Sitemap: https://verifyjobs.org/sitemap.xml
Sitemap: https://verifyjobs.org/ai-sitemap.xml

Host: verifyjobs.org