# ShortSync Robots.txt
# https://www.shortsync.app (canonical domain)

User-agent: *
Allow: /
Allow: /docs/
Allow: /docs/*
Disallow: /api/
Disallow: /dashboard/
Disallow: /_next/
Disallow: /forgot-password
Disallow: /reset-password
# Google keeps parsing REST paths out of code blocks in /docs/api/* (e.g.
# `POST /uploads`) and trying to crawl them as if they were pages on
# www.shortsync.app. They 404 correctly, but blocking here prevents
# re-crawls and stops new phantoms from appearing in Search Console.
Disallow: /uploads
Disallow: /uploads/
Disallow: /posts
Disallow: /posts/
Disallow: /connections
Disallow: /connections/
Disallow: /me
Disallow: /complete
Disallow: /roll
Disallow: /account
Disallow: /account/

# Sitemap location (canonical URL only)
Sitemap: https://www.shortsync.app/sitemap.xml

# Note: The canonical domain is www.shortsync.app
# Only the canonical domain should be crawled

# Crawl-delay for respectful crawling
Crawl-delay: 1

# Major search engines: no crawl delay. A crawler only obeys its most
# specific group, so the page/phantom-path rules from the * group are
# repeated here (with a bare "Allow: /" they ignored all of it). /_next/ and
# /api/ stay open for these bots: they need /_next/ assets to render pages,
# and some pages load their content from /api/.
User-agent: Googlebot
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
Allow: /
Disallow: /dashboard/
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /uploads
Disallow: /uploads/
Disallow: /posts
Disallow: /posts/
Disallow: /connections
Disallow: /connections/
Disallow: /me
Disallow: /complete
Disallow: /roll
Disallow: /account
Disallow: /account/
Crawl-delay: 0

# Block content-scraping bots used for LLM training datasets. Remove these
# Disallow rules if you'd like ShortSync content to be included.
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

# Note: SEO-research bots (AhrefsBot, SemrushBot, MJ12bot, DotBot) are intentionally
# allowed — they power the backlink/keyword databases that prospects use to evaluate
# competitors. Blocking them would hide ShortSync's profile from those tools.