# 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

# Gritwright, gritwright.com
#
# Our policy is open to everyone: people, search engines and AI systems.
# We want to be cited, so nothing here is blocked. Permission is written out
# agent by agent rather than left to silence, because silence is read as
# refusal by some systems.
#
# Full terms: https://gritwright.com/ai-usage/
#
# Machine-readable entry points. Only Sitemap is a robots.txt directive, so
# the rest are listed here as comments rather than invented directives:
#   Site summary for LLMs: https://gritwright.com/llms.txt
#   Feed:                  https://gritwright.com/rss.xml
#   Markdown of any guide: append .md to its URL, e.g.
#                          https://gritwright.com/strong/first-barbell.md

User-agent: *
Allow: /

# --- OpenAI ---------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# --- Anthropic ------------------------------------------------------
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# --- Google ---------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Google-CloudVertexBot
Allow: /

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

User-agent: Perplexity-User
Allow: /

# --- Microsoft and Bing ---------------------------------------------
User-agent: bingbot
Allow: /

# --- Apple ----------------------------------------------------------
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Meta -----------------------------------------------------------
User-agent: meta-externalagent
Allow: /

# --- Amazon ---------------------------------------------------------
User-agent: Amazonbot
Allow: /

# --- Common Crawl, the source of many training corpora ---------------
User-agent: CCBot
Allow: /

# --- Others ---------------------------------------------------------
User-agent: DuckAssistBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: MistralAI-User
Allow: /

Sitemap: https://gritwright.com/sitemap.xml