# 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

# douglasriches.com
#
# The deal, in one line: search crawlers and AI *search* crawlers are welcome,
# because they send readers here and cite the source. AI *training* crawlers are
# not, because they take the writing and give nothing back.
#
# Terms of use, binding on automated access: https://douglasriches.com/terms
# Copyright and reuse:                       https://douglasriches.com/copyright
# Machine-readable TDM reservation (W3C TDMRep): /.well-known/tdmrep.json
#
# Operating a crawler against this site is acceptance of the terms above.
#
# Keeping this current: vendors add and rename tokens constantly. Check the
# operator's own docs before editing — a misspelled token silently does nothing.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# 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.

# ── Deliberately NOT blocked ─────────────────────────────────────────────
# These index or cite with a link back, which is the whole point of writing in
# public. Blocking them would cost readers and gain nothing:
#   Googlebot · Bingbot · DuckDuckBot · Applebot
#   OAI-SearchBot (ChatGPT search) · Claude-SearchBot · Claude-User
#   PerplexityBot · Amzn-SearchBot · Amzn-User · Meta-WebIndexer

# ── AI training crawlers: not permitted ──────────────────────────────────

# OpenAI. Training only — OAI-SearchBot stays allowed, and OpenAI documents
# these as independent settings.
User-agent: GPTBot
Disallow: /

# Anthropic. Training only — Claude-SearchBot and Claude-User stay allowed.
User-agent: ClaudeBot
Disallow: /

# Google. This token covers Gemini training *and* Gemini grounding — they can't
# be separated. Per Google's docs it has no effect on Google Search inclusion or
# ranking; the cost is that Gemini won't cite these pages at prompt time.
User-agent: Google-Extended
Disallow: /

# Apple. Training only, with no search cost — Applebot stays allowed, so this
# site is still found by Spotlight, Siri and Safari.
User-agent: Applebot-Extended
Disallow: /

# Meta. Training and direct indexing — Meta-WebIndexer stays allowed for citations.
User-agent: meta-externalagent
Disallow: /

# Amazon. Training plus product use — Amzn-SearchBot and Amzn-User stay allowed.
User-agent: Amazonbot
Disallow: /

# Common Crawl. Not a model trainer itself, but the upstream corpus for most
# open training datasets, so this one rule removes the site from many at once.
User-agent: CCBot
Disallow: /

# ── Scrapers and data resellers: not permitted ───────────────────────────

# ByteDance. Documented history of ignoring Disallow — hence the Cloudflare
# side of this (see README, "Legal pages and rights reservation").
User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# You.com. Mixed: powers their search, but also resells content through an LLM
# data API. The API side outweighs the referral traffic for a site this size.
User-agent: YouBot
Disallow: /

# ── Undocumented or legacy tokens ────────────────────────────────────────
# None of these appear in their vendor's current documentation. Listed
# defensively; expect them to do nothing.

User-agent: anthropic-ai
Disallow: /

User-agent: claude-web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: FacebookBot
Disallow: /

Sitemap: https://douglasriches.com/sitemap-index.xml