# LingoDew robots.txt — canonical host is https://www.lingodew.com/
# Plain-language site overview for AI assistants: https://www.lingodew.com/llms.txt

# AI retrieval and training crawlers are welcome; being citable by AI
# assistants is a distribution channel, not a threat. These groups are
# explicit for robustness — the catch-all below already allows everything.

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: *
Allow: /

# Video pages already carry the transcript in their HTML; the JSON next to them
# only spends Google's crawl. AI retrievers above keep access to it.
User-agent: Googlebot
Allow: /
Disallow: /*/transcript.json

Sitemap: https://www.lingodew.com/sitemap-index.xml