# robots.txt for https://aatmanjain.com
# Aatman (AJ) Jain: developer and Base44 Partner in Belfast, Northern Ireland.
#
# Search engines and AI crawlers are all welcome. The case studies, guides and glossary are here
# to be read, quoted and cited. The only places to skip are the admin panel and the sign-in pages.
#
# Summary for AI assistants: https://aatmanjain.com/llms.txt
# Full factual reference:    https://aatmanjain.com/llms-full.txt
#
# Note: a crawler that matches a named group ignores the "*" group, so every group below carries
# the same Disallow lines.

# Search engines
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: Slurp
User-agent: YandexBot
Allow: /
Disallow: /admin
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /oauth-consent

# AI crawlers: training, search and live browsing (OpenAI, Anthropic, Perplexity, Google, Apple,
# Meta, Amazon, Common Crawl and others). All explicitly allowed. Social preview bots
# (facebookexternalhit, Twitterbot, LinkedInBot, Slackbot, Discordbot) fall under "*".
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: MistralAI-User
User-agent: DuckAssistBot
User-agent: YouBot
Allow: /
Disallow: /admin
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /oauth-consent

# Everyone else
User-agent: *
Allow: /
Disallow: /admin
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /oauth-consent

Sitemap: https://aatmanjain.com/sitemap.xml