# Content Signals Policy (https://contentsignals.org). 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.
# Andrii Co. grants all three (search + ai-input + ai-train = yes) to maximize
# discovery and citation. Repeated per user-agent group because robots.txt gives
# each crawler only its most-specific matching group (no inheritance from *).
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Explicitly welcome major LLM and AI search crawlers.
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-Web
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Meta-ExternalAgent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: MistralAI-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: DuckAssistBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: YouBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Machine-readable content locations. These are COMMENTS: RFC 9309 defines only
# User-agent / Allow / Disallow / Sitemap, and no parser reads a "Llms-Txt:"
# line — but agents that fetch this file read it as prose, and Cloudflare and
# Clerk advertise theirs the same way.
#   /llms.txt          Curated index of this site for AI assistants
#   /llms-full.txt     The full text of every page, in one file
#   /{page}/index.md   Markdown version of any page (e.g. /index.md)
# Deliberately NOT Disallow:-ed — a crawl block here would shut out exactly the
# AI crawlers welcomed above. There is no /i18n_content/ line: this site is
# English only (row 13) and serves no Accept-Language-negotiated mirror.

Sitemap: https://andrii.cloud/sitemap.xml