# Every crawler is welcome here, AI assistants included. We want to be read,
# quoted, and cited. The rules below only fence off URLs that are machinery,
# not content.
User-agent: *
Allow: /

# Content Signals (contentsignals.org). The same "please read us" posture as
# above, stated in the machine-readable form. All three are `yes` on purpose:
#   ai-train  — training on this corpus is fine
#   search    — index us and link back
#   ai-input  — ground answers in these pages and cite them
# AI assistants are how people find these apps now. Fencing that off would cost
# us the referrals we actually want.
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Data endpoints and HTMX fragments. Not pages, never useful in an index.
Disallow: /api/

# Iframe-only badge widget. Duplicates listings that already have real pages.
Disallow: /embed/

# Server-side redirects into our admin tooling.
Disallow: /review
Disallow: /app/*/edit

# NOTE: /sign-in and /sign-up are intentionally *not* listed here.
# They carry `noindex` in their HTML, and a crawler has to be allowed to fetch
# a page before it can see that directive. Disallowing them would leave them
# eligible for URL-only indexing forever.

Sitemap: https://faith.tools/sitemap.xml