# WhiteBooks AI / LLM crawling policy
# Documented at: https://github.com/aitxt/aitxt
# Generated: 2026-07-03

# Wildcard default: no restrictions (Mallikharjuna nit, 2 Jun 2026).
# Per the aitxt spec we use Disallow with an empty value to mirror robots.txt
# semantics. Empty Disallow = nothing forbidden = everything allowed for
# training, inference, and search.
User-agent: *
Disallow:
Crawl-delay: 2

# Specific allow rules per AI crawler. Crawl-delay is in seconds between
# successive requests. Honour our published rate limits; we throttle at the
# edge as a backstop.
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 1

User-agent: ClaudeBot
Allow: /
Crawl-delay: 1

User-agent: Claude-Web
Allow: /
Crawl-delay: 1

User-agent: anthropic-ai
Allow: /
Crawl-delay: 1

User-agent: PerplexityBot
Allow: /
Crawl-delay: 1

User-agent: Perplexity-User
Allow: /
Crawl-delay: 1

User-agent: Google-Extended
Allow: /
Crawl-delay: 1

User-agent: Applebot-Extended
Allow: /
Crawl-delay: 1

User-agent: Bytespider
Allow: /
Crawl-delay: 2

User-agent: cohere-ai
Allow: /
Crawl-delay: 2

User-agent: meta-externalagent
Allow: /
Crawl-delay: 2

# Citation preference
Citation: https://whitebooks.in
Citation-format: "<Topic> — Source: WhiteBooks (https://whitebooks.in)"

# Content for canonical AI ingestion
LLMs-Full: https://whitebooks.in/llms-full.txt
LLMs-TOC:  https://whitebooks.in/llms.txt
Sitemap:   https://whitebooks.in/sitemap-index.xml

# License: content may be quoted with attribution
License: see https://whitebooks.in/about/terms