# robots.txt for sambanova.ai — corrected by CrawlCheck, 2026-11-03
# Source: the file the site served at the time. Every change is listed here; nothing else was touched.
# Changes:
#   - Added a Sitemap line: https://sambanova.ai/sitemap.xml answered 200 with XML but the file never named it.
#   - 1 named group lacked Disallow lines the * group carries. A crawler obeys only its own most specific group and ignores *, so those rules never applied to it. Copied in.
# Verify after publishing: curl -sI https://sambanova.ai/robots.txt must show text/plain, on the bare URL, with no cache-buster.

User-agent: *
Disallow: /conf/
Disallow: /ref/
Disallow: /lp/ug/
Disallow: /gqyzy8znpnvt3jeptf1q-resources/
Disallow: /gqyzy8z56npnvt3jeptf1q-video/
Disallow: /0vvnpexkh23cmhske3qn-blog/
Disallow: /3diymhwi23-press-release/
Disallow: /jrb7ema3gwz2-news-blog/
Disallow: /samba-academy
Disallow: /academy/welcome-to-samba-academy
Disallow: /academy/getting-started-sambacloud
Disallow: /academy/evolving-market-of-ai

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Googlebot-News
Disallow: /
Allow: /press/
Allow: /news/
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*
Disallow: /conf/
Disallow: /ref/
Disallow: /lp/ug/
Disallow: /gqyzy8znpnvt3jeptf1q-resources/
Disallow: /gqyzy8z56npnvt3jeptf1q-video/
Disallow: /0vvnpexkh23cmhske3qn-blog/
Disallow: /3diymhwi23-press-release/
Disallow: /jrb7ema3gwz2-news-blog/
Disallow: /samba-academy
Disallow: /academy/welcome-to-samba-academy
Disallow: /academy/getting-started-sambacloud
Disallow: /academy/evolving-market-of-ai

Sitemap: https://sambanova.ai/sitemap.xml