# ------------------------------------------------
# AIPOSTIE Robots.txt
# Controls what web crawlers are allowed to index
# Updated: 2025-10-29.2
# ------------------------------------------------
# Website: https://aipostie.com
# Author: MyCoachBuddy Pty Ltd / Richard J. Baker
# Purpose: Allow legitimate search indexing while blocking
#          AI data harvesting and sensitive directories
# ------------------------------------------------

User-agent: *
Allow: /
Allow: /demo/
Allow: /contact/
Allow: /pricing/
Allow: /aiparcelbox/
Crawl-delay: 5

# ------------------------------------------------
# Disallow private/system directories
# ------------------------------------------------
Disallow: /admin/
Disallow: /contact/logs/
Disallow: /includes/
Disallow: /mailbox_data/
Disallow: /widget/
Disallow: /cgi-bin/
Disallow: /tmp/

# ------------------------------------------------
# Sitemap references (for Google, Bing, DuckDuckGo, etc.)
# ------------------------------------------------
# Primary sitemap (AIPOSTIE)
Sitemap: https://aipostie.com/sitemap.xml

# Secondary sitemap (AIParcelBox)
Sitemap: https://aipostie.com/aiparcelbox/sitemap.xml

# Optional: IndexNow endpoint (Bing/Yandex compatibility)
# See: https://www.indexnow.org/
# Host: aipostie.com
# Key: your_indexnow_key_here (if used)

# ------------------------------------------------
# AI and Large-Language-Model Crawler Restrictions
# Prevent AI training or data collection while
# allowing legitimate search engines to index pages.
# ------------------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ChatGPT
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

# ------------------------------------------------
# End of File
# ------------------------------------------------