User-agent: *
Allow: /

# /guia/ (Centro de ventas) is UNLISTED — shared by link only.
#
# It is deliberately NOT disallowed here. A Disallow would stop Google fetching it,
# and a page Google cannot fetch is a page whose noindex it never sees — so a single
# inbound link anywhere would be enough for the bare URL to show up in results, with
# no way for us to remove it. Keeping it crawlable is what lets the noindex work.
# De-indexing is enforced instead by an X-Robots-Tag header on /guia/* (vercel.json)
# plus a meta robots tag, and it is absent from the sitemap, llms.txt and every
# internal link. The AI crawlers below are a different case and DO get a Disallow:
# they ingest rather than index, so noindex buys us nothing with them.

# /og/ must stay crawlable. facebookexternalhit, Twitterbot and LinkedInBot all
# honour robots.txt when they fetch og:image, so disallowing it breaks the link
# preview card on every page that points at /og/*.png.

# AI crawlers — explicitly welcome for GEO/AEO indexing.
# NOTE: a named User-agent block replaces the `*` block for that bot; it does not
# add to it. So any future `Disallow:` added under `*` will NOT apply to the bots
# listed below — it has to be repeated in each block that should honour it.
User-agent: GPTBot
Allow: /
Disallow: /guia/

User-agent: ClaudeBot
Allow: /
Disallow: /guia/

User-agent: PerplexityBot
Allow: /
Disallow: /guia/

User-agent: anthropic-ai
Allow: /
Disallow: /guia/

User-agent: cohere-ai
Allow: /
Disallow: /guia/

Sitemap: https://www.kontempo.io/sitemap.xml