# robots.txt — Rizzo Electric USA
# Spec: https://developers.google.com/search/docs/crawling-indexing/robots/intro

User-agent: *
Allow: /

# Confirmation + utility pages should not be indexed (no organic value, may
# confuse SERPs when the conversion form has already been submitted).
Disallow: /request-received
Disallow: /approved/
Disallow: /404
Disallow: /api/

# Asset directories are crawlable (Google wants to render the page with CSS+JS+images)
Allow: /img/
Allow: /lottie/

# Big AI crawlers — explicitly allowed. Listed individually so the policy is
# visible in the file rather than implicit. If we ever need to opt out of any
# of these, swap Allow: / for Disallow: / under that user-agent.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Sitemap + feed
Sitemap: https://www.rizzoelectricusa.com/sitemap-index.xml
# RSS feed for the blog (not a sitemap, but worth advertising)
# Feed URL: https://www.rizzoelectricusa.com/rss.xml