# 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

# Simplaq — robots.txt
# https://simplaq.com
# Generated by scripts/generate-robots.ts — do not edit by hand.
#
# robots.txt groups do not inherit rules, so every allowed group below
# repeats the same Allow/Disallow body.
#
# AI policy: classic search and AI search/RAG crawlers are allowed so
# Simplaq can be indexed and cited. Model-training-only crawlers get
# Disallow: / so this file agrees with Content-Signal ai-train=no.

Content-Signal: search=yes, ai-input=yes, ai-train=no

# Search engines and social-preview crawlers
User-agent: Googlebot
User-agent: Google-Agent
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: DuckAssistBot
User-agent: Baiduspider
User-agent: YandexBot
User-agent: Applebot
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: LinkedInBot
User-agent: Pinterestbot
Allow: /

# Non-public application surfaces
Disallow: /api/
Disallow: /admin/
Disallow: /auth/
Disallow: /preview/
Disallow: /draft/
Disallow: /internal/

# Legacy WordPress endpoints (no modern equivalent)
Disallow: /wp-json/
Disallow: /wp-admin/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /author/
Disallow: /tag/
Disallow: /feed/
Disallow: /comments/
Disallow: /trackback/
Disallow: /oembed/
Disallow: /xmlrpc.php
Disallow: /wp-login.php

# Legacy query-parameter duplicates
Disallow: /*?p=
Disallow: /*?cat=
Disallow: /*?replytocom=
Disallow: /*?page_id=
Disallow: /*?tag=
Disallow: /*?m=
Disallow: /*?attachment_id=
Disallow: /*?feed=
Disallow: /*?trackback=
Disallow: /*?embed=

# Render-critical assets stay crawlable
Allow: /*.css$
Allow: /*.js$
Allow: /assets/

# AI search / answer engines (allowed so Simplaq can be cited)
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: MistralAI-User
User-agent: GitHubCopilotChat
User-agent: YouBot
Allow: /

# Non-public application surfaces
Disallow: /api/
Disallow: /admin/
Disallow: /auth/
Disallow: /preview/
Disallow: /draft/
Disallow: /internal/

# Legacy WordPress endpoints (no modern equivalent)
Disallow: /wp-json/
Disallow: /wp-admin/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /author/
Disallow: /tag/
Disallow: /feed/
Disallow: /comments/
Disallow: /trackback/
Disallow: /oembed/
Disallow: /xmlrpc.php
Disallow: /wp-login.php

# Legacy query-parameter duplicates
Disallow: /*?p=
Disallow: /*?cat=
Disallow: /*?replytocom=
Disallow: /*?page_id=
Disallow: /*?tag=
Disallow: /*?m=
Disallow: /*?attachment_id=
Disallow: /*?feed=
Disallow: /*?trackback=
Disallow: /*?embed=

# Render-critical assets stay crawlable
Allow: /*.css$
Allow: /*.js$
Allow: /assets/

# Model-training-only crawlers — blocked, matching Content-Signal ai-train=no
User-agent: GPTBot
User-agent: Google-Extended
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: DeepseekBot
User-agent: xAI-Bot
Disallow: /

# Every other crawler
User-agent: *
Allow: /

# Non-public application surfaces
Disallow: /api/
Disallow: /admin/
Disallow: /auth/
Disallow: /preview/
Disallow: /draft/
Disallow: /internal/

# Legacy WordPress endpoints (no modern equivalent)
Disallow: /wp-json/
Disallow: /wp-admin/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /author/
Disallow: /tag/
Disallow: /feed/
Disallow: /comments/
Disallow: /trackback/
Disallow: /oembed/
Disallow: /xmlrpc.php
Disallow: /wp-login.php

# Legacy query-parameter duplicates
Disallow: /*?p=
Disallow: /*?cat=
Disallow: /*?replytocom=
Disallow: /*?page_id=
Disallow: /*?tag=
Disallow: /*?m=
Disallow: /*?attachment_id=
Disallow: /*?feed=
Disallow: /*?trackback=
Disallow: /*?embed=

# Render-critical assets stay crawlable
Allow: /*.css$
Allow: /*.js$
Allow: /assets/

# Sitemap index (references every child sitemap)
Sitemap: https://simplaq.com/sitemap.xml

# AI-readable summaries of the site
# https://simplaq.com/llms.txt
# https://simplaq.com/llm.html