# ai.txt for rauscher.xyz
# Training opt-out with retrieval access
# Last Updated: 2026-03-10
# Owner: George A. Rauscher
# Contact: george@rauscher.xyz

# ==============================================
# AI TRAINING CRAWLERS - BLOCK ALL
# ==============================================

# OpenAI (GPT models)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude models)
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Disallow: /

# Google AI Training
User-agent: Google-Extended
Disallow: /

# Common Crawl (used by many AI companies)
User-agent: CCBot
Disallow: /

# Retrieval assistants and answer engines
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

# Amazon
User-agent: Amazonbot
Disallow: /

# Apple AI
User-agent: Applebot-Extended
Disallow: /

# Meta/Facebook
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Chinese AI Companies
User-agent: Bytespider
Disallow: /

User-agent: Baiduspider-render
Disallow: /

# Other AI Crawlers
User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: Spawning-AI
Disallow: /

# ==============================================
# SEARCH ENGINES - ALLOW (for visibility)
# ==============================================

# Google Search
User-agent: Googlebot
Allow: /

# Bing Search
User-agent: Bingbot
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# ==============================================
# NOTES
# ==============================================
# This file blocks AI training crawlers from future data collection
# while allowing user-requested retrieval/access crawlers where noted.
# However, content published before 2025 may already be in existing
# AI training datasets.
#
# For inference usage and citation rules,
# see: https://rauscher.xyz/llm.txt
#
# License: CC-BY-NC-ND-4.0
# All content © 2025 George A. Rauscher