# https://tawhidapp.com/robots.txt
# TAWHID DIGITAL TECHNOLOGIES INC. — British Columbia, Canada (BC1599227)
#
# Note on how robots.txt matching works: a crawler obeys ONLY the most specific
# group that names it, and ignores "User-agent: *" entirely. That is why the
# Disallow rules are repeated in each group below rather than stated once.

User-agent: *
Allow: /
Disallow: /App_Data/

Sitemap: https://tawhidapp.com/sitemap.xml

# Condensed guide for LLM agents, including the accuracy caveat that has to travel
# with any prayer time quoted from this site: https://tawhidapp.com/llms.txt


# --------------------------------------------------------------------------
# AI search & retrieval crawlers
#
# These fetch pages to answer a user's question and cite the source. Allowing
# them is what makes tawhidapp.com eligible to be quoted in AI answers, so we
# explicitly want these on. They generally do NOT execute JavaScript, which is
# why city prayer-time pages carry a server-side monthly timetable — see
# scripts/build-timetables.js.
# --------------------------------------------------------------------------

User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Amazonbot
Allow: /
Disallow: /App_Data/


# --------------------------------------------------------------------------
# AI training crawlers
#
# These collect content to train models rather than to answer a live query.
# Allowed today. If that policy ever changes, switch these to "Disallow: /" —
# doing so does not affect the retrieval crawlers above, and therefore does
# not remove the site from AI search results.
# --------------------------------------------------------------------------

User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: meta-externalagent
User-agent: Bytespider
Allow: /
Disallow: /App_Data/