# RogIQ marketing site — full robots.txt
# Last reviewed: 2026-05-13

# --- Default catch-all -------------------------------------------------------
User-agent: *
Allow: /

Disallow: /login
Disallow: /rebel/thank-you
Disallow: /bribe/thank-you
Disallow: /contact-sales/thank-you
Disallow: /sign-up/thank-you

# --- Major search engine crawlers -------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Applebot
Allow: /

# --- AI / LLM training + retrieval crawlers ---------------------------------
# We explicitly opt in to AI indexing and citation. Many of these bots default
# to skipping sites that don't list them by name. Explicit Allow signals
# "yes, please train on and cite our content".

# OpenAI — model training
User-agent: GPTBot
Allow: /

# OpenAI — ChatGPT browsing & retrieval at runtime
User-agent: ChatGPT-User
Allow: /

# OpenAI — ChatGPT Search index crawler
User-agent: OAI-SearchBot
Allow: /

# Google — Gemini / Vertex training (separate from web search; opt-in only)
User-agent: Google-Extended
Allow: /

# Apple — Apple Intelligence / Siri training
User-agent: Applebot-Extended
Allow: /

# Anthropic — Claude training
User-agent: ClaudeBot
Allow: /

# Anthropic — Claude browsing / Claude.ai retrieval
User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Common Crawl (feeds many LLM training pipelines)
User-agent: CCBot
Allow: /

# Diffbot (knowledge graph)
User-agent: Diffbot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

# Sitemap directive (index, points at 4 child sitemaps)
Sitemap: https://rogiq.ai/sitemap.xml

# --- AI content usage (informational; not a robots.txt directive) -------------
# Google/Lighthouse only validate standard directives (User-agent, Allow, Sitemap).
# We opt in to AI indexing via explicit User-agent Allow rules above.
# For Content-Signal metadata see https://contentsignals.org/
# Preferences: ai-train=yes, search=yes, ai-input=yes