# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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

# RevenueSpark — robots.txt
# Adalo Blueprint v2.0 §10: as a GEO agency, blocking AI crawlers is self-disqualifying.
# Both training crawlers (GPTBot, anthropic-ai, Google-Extended) and inference crawlers
# (ChatGPT-User, ClaudeBot, PerplexityBot) are explicitly allowed across the public site.
# Sensitive surfaces (admin, internal APIs) are denied to all user-agents.

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

# Inference / RAG crawlers — must be allowed for live AI search citations.
User-agent: ChatGPT-User
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: ClaudeBot
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: Claude-Web
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: PerplexityBot
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: Perplexity-User
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

# Training crawlers — allowed for public marketing content.
User-agent: GPTBot
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: anthropic-ai
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: Google-Extended
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: CCBot
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: Bytespider
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

User-agent: cohere-ai
Allow: /
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/internal/

Sitemap: https://revenuespark.ai/sitemap-index.xml