# AissenceAI SEO Robots Configuration
# This file guides search engine crawlers on how to index our site

# Allow all bots by default
User-agent: *
Allow: /

# Disallow private/admin areas
Disallow: /admin/
Disallow: /api/
Disallow: /private/
Disallow: /dashboard/settings/
Disallow: /auth/

# Allow specific search engine bots
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

# AI Crawlers — explicitly allowed for GEO visibility
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: meta-externalagent
Allow: /

# Crawl delay for general bots
User-agent: *
Crawl-delay: 1

# Higher crawl rate for Google
User-agent: Googlebot
Crawl-delay: 0.5

# Sitemap locations
Sitemap: https://aissence.ai/sitemap.xml
Sitemap: https://aissence.ai/sitemap-blog.xml

# LLMs.txt for AI engines
# https://aissence.ai/llms.txt

# Allow crawling of important content
User-agent: *
Allow: /blog/
Allow: /pricing/
Allow: /roadmap/
Allow: /careers/
Allow: /tutorials/
Allow: /features/
Allow: /enterprise/
Allow: /contact/
Allow: /privacy-policy/
Allow: /terms-of-service/
Allow: /refund-policy/
Allow: /compare/
Allow: /is-it-safe/
Allow: /changelog/
Allow: /interview-guides/
Allow: /llms.txt

# Disallow specific bot traps and duplicate content (allow legitimate query params for pagination/filtering)
Disallow: /search?
Disallow: /*sort=
Disallow: /*filter=
Disallow: /*utm_
Disallow: /*ref=
Disallow: /*fbclid=
Disallow: /*gclid=
Disallow: /session/
Disallow: /temp/
Disallow: /cache/

# Allow images and static assets
User-agent: *
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.css$
Allow: /*.js$

# Block specific bots that waste crawl budget
User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Semrush
Allow: /

User-agent: Ahrefs
Allow: /