# robots.txt for Acculink CPA (acculinkcpa.com)
# Allows search engines and AI / LLM crawlers.
# Blocks admin panel, temp uploads, and DB schema docs.

# ---------- Default rules (all crawlers) ----------
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /uploads/temp/
Disallow: /database-schema/

# ---------- AI / LLM crawlers (explicitly allowed) ----------

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google (separate opt-in for Gemini / AI Overviews training)
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Common Crawl (feeds many open LLMs)
User-agent: CCBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# ByteDance (TikTok / Doubao)
User-agent: Bytespider
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Amazon Alexa+ / Rufus
User-agent: Amazonbot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

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