# robots.txt for https://certain.com

# =============================================================================
# DEFAULT RULE - Allow all crawlers
# =============================================================================

User-agent: *
Allow: /

# =============================================================================
# TRADITIONAL SEARCH ENGINES
# =============================================================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

# =============================================================================
# LLM CRAWLERS - Welcome!
# AI discovery file: https://certain.com/llms.txt
# Full Q&A knowledge base: https://rozz.certain.com/llms-full.txt
# =============================================================================

# --- Anthropic (Claude) ---
User-agent: ClaudeBot
Allow: /
Crawl-delay: 0

User-agent: Claude-SearchBot
Allow: /
Crawl-delay: 0

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

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

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 0

User-agent: ChatGPT-User
Allow: /

# --- Perplexity ---
User-agent: PerplexityBot
Allow: /
Crawl-delay: 0

User-agent: PerplexityUser
Allow: /

# --- Google AI ---
User-agent: Google-Extended
Allow: /

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

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

User-agent: Meta-ExternalFetcher
Allow: /

# --- Other LLM Providers ---
User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

# =============================================================================
# SITEMAPS & DISCOVERY
# =============================================================================

Sitemap: https://certain.com/sitemap_index.xml
Sitemap: https://rozz.certain.com/sitemap.xml

# LLM discovery files (https://llmstxt.org/)
# /llms.txt - Company overview, products, key questions, and links to full content
# Full Q&A knowledge base with inline answers: https://rozz.certain.com/llms-full.txt
# Structured API: https://rozz.certain.com/api/qna.json