# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Signal Mama · robots.txt
# All crawlers welcome — content is public-facing and built for discovery.

User-agent: *
Allow: /

# Internal / app surfaces — noindex preferred (not in sitemap, but block crawl too)
Disallow: /dashboard*
Disallow: /onboarding*
Disallow: /chrome-mockup*
Disallow: /debug*
Disallow: /AUDIT-
Disallow: /ROADMAP-
Disallow: /DATA-SOURCING-
Disallow: /TEMPLATES-PLAN-
Disallow: /logo-preview*

# Legacy / archived
Disallow: /hero-v
Disallow: /glossary-v1.html$

# Crawl-delay only for aggressive bots (most respect this)
User-agent: AhrefsBot
Crawl-delay: 5

User-agent: SemrushBot
Crawl-delay: 5

# AI crawlers — explicit allow; we want the docs corpus indexable
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

# Sitemap
Sitemap: https://signalmama.com/sitemap.xml