# 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.

# BEGIN Cloudflare Managed content

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

# ahmeego.com — Crawler & AI Agent Directives
# Updated: 2026-05-02
# Wikidata: https://www.wikidata.org/wiki/Q139620020

# Content Signals (per Cloudflare standard)
# search=yes: allow search indexing
# ai-input=yes: allow AI retrieval/grounding (RAG, Cloudflare AI agents, etc.)
# ai-train=no: do NOT use for model training/fine-tuning

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
Allow: /services/
Allow: /ecommerce/
Allow: /blog/
Allow: /tools/
Allow: /tools/argus/
Allow: /course/
Allow: /training/
Allow: /sitemaps/
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /.well-known/ai-plugin.json
Allow: /agents.json
Disallow: /api/
Disallow: /admin/
Disallow: /training/admin/
Disallow: /training/exam.html
Disallow: /training/results.html
Disallow: /training/cert.html
Disallow: /*?sort=
Disallow: /*?filter=

# ============================================================
# AI training crawlers — BLOCKED (do not use content for model training)
# ============================================================

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: PiplBot
Disallow: /

User-agent: PanguBot
Disallow: /

# ============================================================
# AI retrieval / grounding bots — ALLOWED (citation, not training)
# These are the bots that bring live traffic via AI answers
# ============================================================

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

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

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

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

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

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

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

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

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

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

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

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

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

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

# Sitemaps — sitemap index referencing core pages, blog, ARGUS reports, and tier-1 indexed service/ecommerce pages
Sitemap: https://ahmeego.com/sitemap.xml
Sitemap: https://ahmeego.com/api/argus-sitemap