# robots.txt — doseedo.com
# Marketing pages are static HTML, served verbatim (no JS needed to read them).
# Search engines and AI assistants are welcome. App, API, auth and downloads are off-limits.

# Default — every compliant crawler
User-agent: *
Allow: /
Disallow: /api/
Disallow: /app
Disallow: /tools/
Disallow: /downloads/
# Pre-rendered locale variants are served at /es/, /ja/… (clean URLs, listed in
# sitemap-i18n.xml and pointed at by every page's hreflang cluster). The raw
# generated files under /i18n/<lang>/… are the same pages at a second address —
# blocked so they never compete with the URLs we actually want ranked.
Disallow: /i18n/
# The workbench (/dev/landing, /dev/marketing, /dev/daw-ui, and the app's dev
# routes) is ADMIN-ONLY as of 2026-08-25 — middleware.ts 404s it for everyone
# else, so a crawler gets nothing there anyway. Kept as belt and braces, and so
# the URLs drop out of any index that still holds them. What production serves
# is the published bake at /site/, which is deliberately NOT disallowed: the
# home page's film, footage and melodies live there, and Google has to be able
# to fetch a page's assets to render it. /site/landing.html canonicalises to
# "/" the same way /convert.html does, so it never ranks as a second home page.
Disallow: /dev/
Disallow: /jam/
Disallow: /sign-in
Disallow: /sign-up
Disallow: /after-signin
Disallow: /sso-callback
Disallow: /verify
Disallow: /token
Disallow: /register
Disallow: /logout

# Search engines + AI assistants (training and live retrieval) — explicitly welcomed.
# Listing them in one group so an override-on-name still inherits the off-limits paths.
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
Allow: /
Disallow: /api/
Disallow: /app
Disallow: /tools/
Disallow: /downloads/
# Pre-rendered locale variants are served at /es/, /ja/… (clean URLs, listed in
# sitemap-i18n.xml and pointed at by every page's hreflang cluster). The raw
# generated files under /i18n/<lang>/… are the same pages at a second address —
# blocked so they never compete with the URLs we actually want ranked.
Disallow: /i18n/
# The workbench (/dev/landing, /dev/marketing, /dev/daw-ui, and the app's dev
# routes) is ADMIN-ONLY as of 2026-08-25 — middleware.ts 404s it for everyone
# else, so a crawler gets nothing there anyway. Kept as belt and braces, and so
# the URLs drop out of any index that still holds them. What production serves
# is the published bake at /site/, which is deliberately NOT disallowed: the
# home page's film, footage and melodies live there, and Google has to be able
# to fetch a page's assets to render it. /site/landing.html canonicalises to
# "/" the same way /convert.html does, so it never ranks as a second home page.
Disallow: /dev/
Disallow: /jam/
Disallow: /sign-in
Disallow: /sign-up
Disallow: /after-signin
Disallow: /sso-callback
Disallow: /verify
Disallow: /token
Disallow: /register
Disallow: /logout

Sitemap: https://doseedo.com/sitemap.xml
Sitemap: https://doseedo.com/sitemap-i18n.xml
Sitemap: https://doseedo.com/sitemap-video.xml

# For AI assistants: a curated index lives at https://doseedo.com/llms.txt
# and the full text of every page at https://doseedo.com/llms-full.txt