# 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

# robots.txt for Linear Learn
# AUTO-GENERATED by scripts/build-seo-assets.mts — do not edit by hand.
# Policy lives in src/lib/seo/{routes,crawlers}.ts.

User-agent: *
Allow: /
# `Disallow:` is a prefix match and the longest match wins, so the indexable
# pages nested under a disallowed prefix have to be allowed back explicitly.
Allow: /learn/map
Allow: /learn/dojo
Allow: /learn/tech
# learner dashboard — per-account state
Disallow: /learn
# code studio — session workspace
Disallow: /learn/studio
# study plans — per-account state
Disallow: /learn/plans
# mobile drill deck — session workspace
Disallow: /learn/mobile
# scene book — deep-linked companion views
Disallow: /learn/scenes
# mind map deck — deep-linked companion views
Disallow: /learn/mind-maps
# account settings
Disallow: /profile
# authenticated checkout
Disallow: /store
# authenticated interview records
Disallow: /interviews
# authenticated scheduling
Disallow: /calendly
# local-dev sandbox; 404s in production
Disallow: /experiments
# back-office console — admin-only
Disallow: /admin
# tokenised auth flow
Disallow: /reset-password
# booking flow — per-invitee links
Disallow: /book
# booking management — per-invitee links
Disallow: /manage

# Answer engines — same access as any search crawler. These fetch a page to
# answer a live question and cite it, so blocking them would remove the site
# from AI answers without protecting anything.
#   OAI-SearchBot — OpenAI — ChatGPT search index
#   ChatGPT-User — OpenAI — user-initiated fetch
#   Claude-User — Anthropic — user-initiated fetch
#   Claude-SearchBot — Anthropic — search result fetch
#   PerplexityBot — Perplexity — search index
#   Perplexity-User — Perplexity — user-initiated fetch
#   DuckAssistBot — DuckDuckGo — DuckAssist
#   MistralAI-User — Mistral — Le Chat fetch
#   Applebot — Apple — Siri & Spotlight
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: Applebot
Allow: /

# Training-only crawlers — no referral, no citation. Disallowed. These tokens
# are distinct from the search/answer ones above: blocking Google-Extended
# does not affect Google Search, and blocking Applebot-Extended does not
# affect Siri.
#   GPTBot — OpenAI — model training
#   Google-Extended — Google — Gemini training (not Search)
#   Applebot-Extended — Apple — model training (not Siri)
#   Meta-ExternalAgent — Meta — model training
#   CCBot — Common Crawl — open training corpus
#   Bytespider — ByteDance — model training
#   Diffbot — Diffbot — knowledge graph scrape
#   Omgilibot — Webz.io — dataset resale
#   ImagesiftBot — Imagesift — image dataset
#   anthropic-ai — Anthropic — retired training token
#   cohere-ai — Cohere — model training
#   PanguBot — Huawei — model training
#   Timpibot — Timpi — dataset crawl
User-agent: GPTBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: CCBot
User-agent: Bytespider
User-agent: Diffbot
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: PanguBot
User-agent: Timpibot
Disallow: /

Sitemap: https://linearpad.linearbits.com/sitemap.xml
# LLM-readable index: https://linearpad.linearbits.com/llms.txt