User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/

# brand_assets is deliberately crawlable. It holds the favicons, og-image.png,
# the Organization logo, and every blog thumbnail. Blocking it made Google show
# a default globe instead of the favicon in search results, and hid the
# thumbnails from Images and Discover.
#
# Nothing private lives here. The only non-image file, Brand Kit.md, is excluded
# by .gitignore so it never reaches the deploy at all (verified 404 in
# production). robots.txt is an advisory request to crawlers, not an access
# control, and naming a path here advertises it. Keep secrets out of the deploy
# instead, which is what .gitignore and .vercelignore already do.

# AI citation and retrieval bots (ALLOW these, they power ChatGPT/Claude/Perplexity answers)

# User-triggered fetchers: a person asked the assistant and it went to look
User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

# Search-index crawlers: these build the index that produces citations
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# AI training scrapers (BLOCK these, they scrape for model training, not citation)
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: img2dataset
Disallow: /

Sitemap: https://www.socialvik.com/sitemap.xml