# robots.txt for StackEnhance
# https://stackenhance.com
#
# Public: the start pages (/, /se, /signal, /studio and their /se twins), the
# brand directory and brand pages (/brands…, /se/brands…), blog, help,
# pricing and legal.
#
# The logged-in app is listed below so crawlers do not spend time on it. Share
# links, invitations, onboarding and the Studio prospect pages are NOT listed
# on purpose: they carry `X-Robots-Tag: noindex` (vercel.json), and a crawler
# can only read that header on a URL it is allowed to fetch — a disallowed URL
# that someone links can still be indexed by its address alone, which for a
# share link or a prospect page is exactly what must not happen.
#
# Prefix rules: `/signal/` and `/studio/` (trailing slash) leave the public
# /signal and /studio start pages crawlable; `/brand/` (the app) does not match
# the public `/brands/`.

User-agent: *
Allow: /

# API (the brand pages and sitemaps reach crawlers through rewrites, not /api)
Disallow: /api/

# The logged-in app
Disallow: /signal/
Disallow: /admin
Disallow: /dashboard
Disallow: /emails
Disallow: /brand/
Disallow: /campaigns
Disallow: /calendar
Disallow: /compare
Disallow: /competitors
Disallow: /analytics
Disallow: /benchmarks
Disallow: /inspiration
Disallow: /subject-lines
Disallow: /time-machine
Disallow: /marketing-plan
Disallow: /imports
Disallow: /notifications
Disallow: /settings

# Internal
Disallow: /design-system/
Disallow: /resources

# SEO-tool and data-reseller crawlers, blocked (owner, 2026-11-01). They bring
# no visitors and no AI answers; AhrefsBot alone was 40 % of all requests in
# October (420k of ~1.05M) and pushed the Hobby plan past its limit. A named
# group replaces `*` for that bot, so these get only the Disallow below.
# AI assistants and search engines (GPTBot, OAI-SearchBot, ChatGPT-User,
# ClaudeBot, Claude-User, Claude-SearchBot, PerplexityBot, Google-Extended,
# Applebot, Amazonbot, CCBot, Meta, Mistral, DuckDuckGo, Bing, Google, Exa…)
# are deliberately NOT listed: they follow the `*` group above.
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: SemrushBot
User-agent: SiteAuditBot
User-agent: SplitSignalBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: serpstatbot
User-agent: Barkrowler
User-agent: MegaIndex
User-agent: SEOkicks
User-agent: SeekportBot
User-agent: PetalBot
User-agent: AspiegelBot
User-agent: Bytespider
User-agent: ZoominfoBot
User-agent: magpie-crawler
User-agent: Screaming Frog SEO Spider
User-agent: SERankingBacklinksBot
User-agent: AwarioBot
User-agent: Reflectionbot
User-agent: ElevenlabsCrawler
User-agent: AionBot
User-agent: TokenFoundryBot
User-agent: QlyzeBot
User-agent: TernCrawler
User-agent: SQLSpider
User-agent: SpiderLing
User-agent: SenderBot
Disallow: /

# sitemap-index.xml lists sitemap.xml (every public page, generated at build)
# and sitemap-brands.xml (every indexable brand page, from the backend).
Sitemap: https://stackenhance.com/sitemap-index.xml

# ARD manifest for AI agents (Lighthouse "agentic" audit reads this line first,
# then /.well-known/ai-catalog.json). Search crawlers ignore unknown directives.
Agentmap: https://stackenhance.com/.well-known/ai-catalog.json