# Every page and asset is open to every crawler, search engine and AI assistant.
# Query-string URLs are not blocked: each page carries a canonical tag.
User-agent: *
Allow: /

# Named AI crawlers and assistants, listed so the intent is explicit.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bingbot
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Amazonbot
User-agent: Bytespider
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: cohere-ai
User-agent: YouBot
Allow: /

# All three hostnames share this one docroot, so siteqwality.de/robots.txt and
# siteqwality.it/robots.txt serve this same file. A robots.txt Sitemap directive is only
# honoured for its own host unless the sitemap is cross-submitted, so listing only the .com
# sitemap left the two ccTLDs with no discoverable sitemap at all. All three are listed here
# so every host finds its own. sitemap.xml.php is host-aware and serves the right set.
Sitemap: https://siteqwality.com/sitemap.xml
Sitemap: https://siteqwality.de/sitemap.xml
Sitemap: https://siteqwality.it/sitemap.xml