# 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 WritersLogic
# https://writerslogic.com

User-agent: *
Allow: /

# Sitemap location
Sitemap: https://writerslogic.com/sitemap.xml

# Disallow internal app pages from indexing
Disallow: /app/*
Disallow: /api/
Disallow: /webhook/
Disallow: /admin/
Disallow: /callback
Disallow: /signout
Disallow: /reset-password

# Confidential business decks — do not index or crawl
Disallow: /pitchdeck
Disallow: /productcatalog
Disallow: /strategy-team
Disallow: /strategy-growth
Disallow: /executive-summary

# Allow all major search engines.
# NOTE (RFC 9309): a crawler obeys only its most-specific user-agent group and
# does NOT inherit the "User-agent: *" Disallow rules, so the confidential paths
# must be repeated in each named indexer group below.
User-agent: Googlebot
Allow: /
Disallow: /callback
Disallow: /pitchdeck
Disallow: /productcatalog
Disallow: /strategy-team
Disallow: /strategy-growth
Disallow: /executive-summary

User-agent: Bingbot
Allow: /
Disallow: /callback
Disallow: /pitchdeck
Disallow: /productcatalog
Disallow: /strategy-team
Disallow: /strategy-growth
Disallow: /executive-summary

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Slurp
Allow: /

# Brave Search
User-agent: BraveBot
Allow: /

# Exa.ai
User-agent: ExaBot
Allow: /

# Apple
User-agent: Applebot
Allow: /

# Facebook
User-agent: facebookexternalhit
Allow: /

# Twitter
User-agent: Twitterbot
Allow: /

# LinkedIn
User-agent: LinkedInBot
Allow: /

# ===== AI Training Opt-Out =====
# We allow AI bots to index for search/discovery but opt out of training

# OpenAI/ChatGPT - Allow search & browsing, disallow training
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Allow: /

# OpenAI SearchGPT crawler (powers search citations, not training)
User-agent: OAI-SearchBot
Allow: /

# Anthropic - Allow search & browsing, disallow legacy training crawler
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Allow: /

# ClaudeBot now serves Claude's web-search citations — allow for discovery
User-agent: ClaudeBot
Allow: /

# Google AI training
User-agent: Google-Extended
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

# Common Crawl (used for AI training)
User-agent: CCBot
Disallow: /

# Perplexity - Allow browsing
User-agent: PerplexityBot
Allow: /

# Bytedance AI
User-agent: Bytespider
Disallow: /

# Facebook AI
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Amazon AI
User-agent: Amazonbot
Disallow: /

# Apple AI training
User-agent: Applebot-Extended
Disallow: /

# ===== SEO Crawlers (rate limited) =====
User-agent: AhrefsBot
Crawl-delay: 10
Disallow: /api/

User-agent: SemrushBot
Crawl-delay: 10
Disallow: /api/

User-agent: MJ12bot
Crawl-delay: 10
Disallow: /api/

# ===== Block bad bots =====
User-agent: dotbot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalBot
Disallow: /