# robots.txt — Uppervox
# Policy: allow all legitimate AI search crawlers + traditional search crawlers.
# Blocks training-only Common Crawl. Allows citation-capable AI bots.

# ── Default: allow everything ──
User-agent: *
Allow: /
Disallow: /assets/cases/.firecrawl/
Disallow: /node_modules/
Disallow: /.git/

# ── AI search bots: explicit allow (so they can cite this site in answers) ──

# OpenAI ChatGPT (search + browse)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
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: /

# Google Gemini + Google AI Overviews
User-agent: Google-Extended
Allow: /

# Microsoft Copilot (via Bing)
User-agent: Bingbot
Allow: /

User-agent: BingPreview
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

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

User-agent: Meta-ExternalFetcher
Allow: /

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

# ── Common Crawl: ALLOWED (2026-09-01) ──
# Common Crawl feeds the training data of many models. Being present in it makes models "know" Uppervox
# before they search — worth more than the training-data concern for a business that sells AI visibility.
User-agent: CCBot
Allow: /

# ── Sitemap ──
Sitemap: https://uppervox.com/sitemap.xml