# ====================================================================
# Robots.txt for barth-gmbh.at
# Optimizing visibility for AI Search Engines (GEO) & LLM scrapers
# ====================================================================

# ALLOW real-time AI searches to access and cite active content
User-agent: OAI-SearchBot
Allow: /

# ALLOW Perplexity to index pages for direct conversational citations
User-agent: PerplexityBot
Allow: /

# ALLOW Anthropic's Claude to read site content for accurate indexing
User-agent: ClaudeBot
Allow: /

# ALLOW Google AI Overviews (SGE) to utilize content in generative answers
User-agent: Google-Extended
Allow: /

# OPTIONAL: Block OpenAI's core training bot from scraping data 
# for upcoming base model training (GPT-5+). 
# Note: OAI-SearchBot (above) bypasses this to allow real-time citations.
User-agent: GPTBot
Disallow: /

# Standard search engine crawlers (Google, Bing, etc.)
User-agent: *
Allow: /
Disallow: /include/
Disallow: /get.php

# Reference to the XML sitemap
Sitemap: https://www.barth-gmbh.at/sitemap.xml