# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Perkusai robots policy
#
# AI assistants / crawlers: use ONLY the dedicated AI endpoints  /api/ai/search  and
# /api/ai/stats. Every OTHER /api/ endpoint is internal (used by the website) and is
# off-limits to bots.
# Discovery: /llms.txt · /openapi.json · /for-ai.html (also .en.html / .ru.html)

# Generic crawlers: site pages yes, the whole API no.
# Content Signals (contentsignals.org): AI may use our content to answer/ground shopping
# queries (ai-input) and surface us in AI search, but not to train models. Adjust as you wish.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /api/
# Cloudflare's own endpoints, not ours. /cdn-cgi/l/email-protection is the target of the link CF
# substitutes for an obfuscated mailto:; it 404s for a crawler and was one of the two "Not found
# (404)" URLs in Search Console. Nothing under /cdn-cgi/ is ever a page of this site.
Disallow: /cdn-cgi/

# AI crawlers / assistants: site pages + the AI endpoint (/api/ai/) are allowed;
# all other /api/ endpoints are disallowed. (Allow is listed first and is the more
# specific path, so /api/ai/ wins over the /api/ Disallow.)
# Grouped user-agents (OpenAI, Anthropic, Google/Gemini, Perplexity, Microsoft/Copilot,
# Apple, Meta, Amazon, ByteDance, DuckDuckGo, You.com, Cohere, Common Crawl):
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: bingbot
User-agent: BingPreview
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: Bytespider
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: cohere-ai
User-agent: CCBot
Allow: /api/ai/
Disallow: /api/

# sitemap.xml is written at build time by web/prerender.js and lists this shopfront's own entry
# pages (landing, /for-ai, /atpigo and /top page 1) in its own languages. The other two are
# generated from the live catalogue and list page 1 of each category - the long-tail pages worth
# ranking, and the only URLs on those two lists that are still index,follow.
Sitemap: https://perkusai.com/sitemap.xml
Sitemap: https://perkusai.com/sitemap-atpigo.xml
Sitemap: https://perkusai.com/sitemap-top.xml