# WaffleInvoice robots.txt
# Default: allow all standard search crawlers.
User-agent: *
Allow: /

# ─────────────────────────────────────────────────────────────────────
# AI / LLM crawlers, EXPLICITLY ALLOWED.
# These power AI answer engines and AI Overviews. Being allowed here is
# what makes WaffleInvoice eligible to be cited/recommended when someone
# asks an assistant for invoice software. Do not block these.
# ─────────────────────────────────────────────────────────────────────

# OpenAI (ChatGPT browsing + training + search)
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /

# Google Gemini / AI Overviews (Google-Extended governs Gemini + Vertex
# training/grounding; standard Googlebot already allowed via * above)
User-agent: Google-Extended
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# Common Crawl (feeds many LLM training sets)
User-agent: CCBot
Allow: /

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

# Microsoft Copilot / Bing
User-agent: bingbot
Allow: /

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

# Meta AI
User-agent: meta-externalagent
Allow: /
User-agent: FacebookBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Sitemaps
Sitemap: https://www.waffleinvoice.com/sitemap.xml