User-agent: Screaming Frog SEO Spider
Allow: /

User-agent: Googlebot
Allow: /
Disallow: /wp-content/uploads/2021/02/TPx-Compliance-Solutions.pdf
Disallow: /wp-content/uploads/2028/2/Service-Level-Agreement-MSx-Datacenters-09-24-19.pdf

User-agent: Bingbot
Allow: / 
Disallow: /wp-content/uploads/2021/02/TPx-Compliance-Solutions.pdf
Disallow: /wp-content/uploads/2028/2/Service-Level-Agreement-MSx-Datacenters-09-24-19.pdf

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

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

User-agent: ClaudeBot         # chat citation fetch
User-agent: claude-web        # web-focused crawl
Allow: /

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

# ——— AMAZON ———
User-agent: Amazonbot
Allow: /

# ——— APPLE ———
User-agent: Applebot
User-agent: Applebot-Extended
Allow: /

# ——— META ———
User-agent: FacebookBot
User-agent: meta-externalagent
Allow: /

# ——— LINKEDIN ———
User-agent: LinkedInBot
Allow: /

# ——— BYTEDANCE ———
User-agent: Bytespider
Allow: /

# ——— DUCKDUCKGO ———
User-agent: DuckAssistBot
Allow: /

# ——— COHERE ———
User-agent: cohere-ai
Allow: /

# ——— ALLEN INSTITUTE / COMMON CRAWL / OTHER RESEARCH ———
User-agent: AI2Bot
User-agent: CCBot
User-agent: Diffbot
User-agent: omgili
Allow: /

# ——— EMERGING SEARCH START-UPS ———
User-agent: TimpiBot
User-agent: YouBot
Allow: /

User-agent: *
Disallow: /

Sitemap: https://www.tpx.com/sitemap_index.xml