# robots.txt for https://prismlearning.academy/
# Allow reputable crawlers to access public content.

User-agent: *
Allow: /

# Block thin / duplicate parameterized list pages from crawl.
# These dilute crawl budget on a new domain and add no index value.
Disallow: /*?*page=
Disallow: /*?*section=
Disallow: /*?*utm_
Disallow: /*?*ref=

# Block auth / checkout / utility paths that should never be indexed.
# These are the real routes on this site (src/pages + public/cart).
Disallow: /admin-login
Disallow: /reset-password
Disallow: /cart
Disallow: /api/

# AI / answer-engine crawlers — explicitly welcomed to read public content
# (same restricted paths as above). Helps PRiSM surface in AI answers.
User-agent: GPTBot
Allow: /
Disallow: /*?*page=
Disallow: /*?*section=
Disallow: /admin-login
Disallow: /reset-password
Disallow: /cart
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /admin-login
Disallow: /reset-password
Disallow: /cart
Disallow: /api/

# OAI-SearchBot is the crawler that builds ChatGPT Search's index — distinct from
# GPTBot (model training) and ChatGPT-User (live user-initiated fetches). Omitting
# it meant PRiSM was opted in to training and live fetches but absent from the
# search index itself.
User-agent: OAI-SearchBot
Allow: /
Disallow: /*?*page=
Disallow: /*?*section=
Disallow: /admin-login
Disallow: /reset-password
Disallow: /cart
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /*?*page=
Disallow: /*?*section=
Disallow: /admin-login
Disallow: /reset-password
Disallow: /cart
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /*?*page=
Disallow: /*?*section=
Disallow: /admin-login
Disallow: /reset-password
Disallow: /cart
Disallow: /api/

# Sitemap (absolute URL). The path is the one named in Suheb's approved sitemap
# structure. This app does NOT serve the index — sitemap_index.xml and its legacy
# alias sitemap.xml are CDN objects (masters in s3-sitemaps/). Their CHILDREN,
# sitemap-main.xml and sitemap-sat-pages.xml, ARE served from public/ by this app.
# Only ONE Sitemap line: /sitemap.xml is kept alive as a legacy alias but must
# not be advertised alongside the index, or the same URL set is submitted twice
# under two names.
Sitemap: https://prismlearning.academy/sitemap.xml