# 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

# AceSense - public marketing site
# Last updated: 2026-04-25
#
# All bots welcome - search, AI search, training crawlers, agents.
# Authenticated app routes live on app.acesense.io and admin.acesense.io
# (separate domains) and are not addressable here, so we don't need to
# disallow them in this file.

User-agent: *
Allow: /

# Search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# AI search bots (citation surfaces)
User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Amzn-SearchBot
Allow: /

User-agent: AzureAI-SearchBot
Allow: /

User-agent: Google-CloudVertexBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleAgent-Mariner
Allow: /

User-agent: Gemini-Deep-Research
Allow: /

User-agent: Grok-DeepSearch
Allow: /

User-agent: xAI-Grok
Allow: /

User-agent: GrokBot
Allow: /

User-agent: meta-webindexer
Allow: /

User-agent: meta-externalfetcher
Allow: /

User-agent: Manus-User
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: NovaAct
Allow: /

User-agent: YouBot
Allow: /

# Training crawlers (explicitly allowed - content licensing is fine for indexing)
User-agent: GPTBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

User-agent: DeepSeekBot
Allow: /

User-agent: PanguBot
Allow: /

User-agent: Webzio-Extended
Allow: /

User-agent: Diffbot
Allow: /

User-agent: omgili
Allow: /

User-agent: omgilibot
Allow: /

User-agent: Timpibot
Allow: /

User-agent: Ai2Bot
Allow: /

User-agent: Ai2Bot-Dolma
Allow: /

User-agent: Claude-Code
Allow: /

User-agent: MyCentralAIScraperBot
Allow: /

User-agent: Google-Agent
Allow: /

User-agent: quillbot.com
Allow: /

Sitemap: https://acesense.io/sitemap.xml