User-agent: *
Allow: /

# Block only form endpoints and outbound-tracking query params.
# We used to also block /jobs? and /compare? for crawl-budget hygiene,
# but that prevented Google from reading the canonical on filtered
# variants and left old indexed URLs stuck in "Indexed, though blocked
# by robots.txt" (2026-07-11 removal). Canonical tags on filter URLs
# now do the job cleanly.
Disallow: /culture-cards/create?
Disallow: /culture-cards/c/
Disallow: /api/cards/
Disallow: /*?ref=
Disallow: /*?utm_

Sitemap: https://jobsbyculture.com/sitemap-index.xml

# LLM / AI agents may crawl the public site, but never private culture cards.
# Multiple User-agent lines form one shared group with the restrictions below.
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Claude-Web
User-agent: Anthropic-AI
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: cohere-ai
User-agent: Bytespider
User-agent: YouBot
User-agent: Amazonbot
User-agent: PhindBot
Allow: /
Disallow: /culture-cards/c/
Disallow: /api/cards/