Sitemap: https://outliyr.com/sitemap_index.xml

# Content Signals (draft-romm-aipref-contentsignals): declarative AI-usage preferences
Content-Signal: ai-train=yes, search=yes, ai-input=yes

User-agent: *
Disallow: /wp-admin/
Disallow: /podcast/*/feed
Disallow: /cdn-cgi/
Allow: /wp-admin/admin-ajax.php
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /trials/
Disallow: /trials/_demo

# LLM index: https://outliyr.com/llms.txt

# ——— OPENAI ———
# Search (shows my webpages as links inside ChatGPT search). NOT used for model training.
User-agent: OAI-SearchBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# User-driven browsing from ChatGPT and Custom GPTs. Acts after a human click.
User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# Model-training crawler. Opt-out here if I don’t want content in GPT-4o or GPT-5.
User-agent: GPTBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /                     # everything else

# ——— ANTHROPIC (Claude) ———
User-agent: anthropic-ai      # bulk model training
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /
User-agent: ClaudeBot         # chat citation fetch
User-agent: claude-web        # web-focused crawl
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— PERPLEXITY ———
User-agent: PerplexityBot     # index builder
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /
User-agent: Perplexity-User   # human-triggered visit
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— GOOGLE (Gemini) ———
User-agent: Google-Extended
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— MICROSOFT (Bing / Copilot) ———
User-agent: BingBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— AMAZON ———
User-agent: Amazonbot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— APPLE ———
User-agent: Applebot
User-agent: Applebot-Extended
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— META ———
User-agent: FacebookBot
User-agent: meta-externalagent
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— LINKEDIN ———
User-agent: LinkedInBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— BYTEDANCE ———
User-agent: Bytespider
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— DUCKDUCKGO ———
User-agent: DuckAssistBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— COHERE ———
User-agent: cohere-ai
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— ALLEN INSTITUTE / OTHER RESEARCH ———
User-agent: AI2Bot
User-agent: Diffbot
User-agent: omgili
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— COMMON CRAWL (training corpus for GPT/Llama/Mistral base models) ———
User-agent: CCBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /

# ——— EMERGING SEARCH START-UPS ———
User-agent: TimpiBot
User-agent: YouBot
Disallow: /login
Disallow: /register
Disallow: /dashboard
Allow: /


# Public profiles: opt out of training, keep search and answer retrieval.
User-agent: GPTBot
Disallow: /u/

User-agent: ClaudeBot
Disallow: /u/

User-agent: anthropic-ai
Disallow: /u/

User-agent: Google-Extended
Disallow: /u/

User-agent: CCBot
Disallow: /u/

User-agent: Bytespider
Disallow: /u/

User-agent: Applebot-Extended
Disallow: /u/