User-agent: *
Allow: /

# Disallow low-value or non-public pages
Disallow: /branding-guidelines
Disallow: /dashboard
Disallow: /sleepless-tradesman.apk

# /signin? callbackUrl variants are auth redirects — not useful to crawl
Disallow: /signin?

# Disallow Next.js static assets — JS/CSS chunks, fonts, media
# These waste crawl budget and should never be indexed
Disallow: /_next/static/

# Disallow API routes
Disallow: /api/

# Allow all major search engine bots explicitly
# Repeat the static-asset and API disallows so they are not overridden by the
# per-bot Allow: / rule (more-specific user-agent blocks take precedence over *)
User-agent: Googlebot
Allow: /
Disallow: /_next/static/
Disallow: /api/
Disallow: /signin?

User-agent: Bingbot
Allow: /
Disallow: /_next/static/
Disallow: /api/
Disallow: /signin?

User-agent: Slurp
Allow: /
Disallow: /_next/static/
Disallow: /api/
Disallow: /signin?

User-agent: DuckDuckBot
Allow: /
Disallow: /_next/static/
Disallow: /api/
Disallow: /signin?

# AI crawlers — allow indexing for AI search and LLM training on public content
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YouBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: cohere-ai
Allow: /

# Sitemaps
Sitemap: https://sleeplesstradesman.com/sitemap.xml
Sitemap: https://sleeplesstradesman.com/image-sitemap.xml
Sitemap: https://sleeplesstradesman.com/quote/sitemap.xml

# RSS feeds (not sitemaps — listed separately for feed readers)
# https://sleeplesstradesman.com/blog/feed.xml

# LLM Information Files
# See https://llmstxt.org for the llms.txt specification
# Concise version: https://sleeplesstradesman.com/llms.txt
# Full version: https://sleeplesstradesman.com/llms-full.txt