# DataAgent marketing site - robots.txt
#
# ─────────────────────────────────────────────────────────────────────────────
#  DEPLOYED DOMAIN: data-agent.me
#
#  This domain is carried in TWENTY-ONE files (seventeen HTML pages in their
#  og:url / og:image tags, this file, sitemap.xml, and the CSP blocks in
#  netlify.toml / vercel.json). If the site moves to another domain, update
#  all of them together.
#
#  The site URL is NOT derived from window.DATAAGENT_REPO_URL in
#  website/js/main.js: that constant is the GitHub repository that publishes
#  the Windows releases, not the web host. Two different things.
# ─────────────────────────────────────────────────────────────────────────────

User-agent: *
Allow: /

# The app renders the legal pages from ROUTES (/legal/privacy.html and
# friends) and fills them in from config/legal.yaml. A crawler that reaches
# an unrendered template must not index it, so the whole route is off-limits.
Disallow: /legal/

# Share links carry a token and a per-view payload. There is nothing there
# for a search engine and a lot for a scraper.
Disallow: /share/

# The sign-in surface is not content. Indexing it is pointless and it drags
# credential pages into search results.
Disallow: /auth/

# website/static/ does not exist in the static site, but the APP mounts its
# SPA at /static/. If the marketing site is ever served from the same
# origin, keep the directory out of the index.
Disallow: /static/

Sitemap: https://data-agent.me/sitemap.xml