# =============================================================================
# robots.txt — stantscherenkow.com
# Last updated: 2026-06-09
# =============================================================================
# Policy: maximum discovery for search engines, AI search, answer engines,
# and LLM retrieval/training crawlers. Do not add a sitewide Disallow rule.
# Keep crawlable public pages available so search engines can follow canonicals,
# redirects, citations, and AI-readable route files.
# =============================================================================

# Default: every crawler unless overridden below
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Allow: /cdn-cgi/image/
Allow: /ai.txt
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /voice-ai.txt
Allow: /humans.txt
Allow: /ai-index.json
Allow: /answers/
Allow: /knowledge/
Allow: /problems/
Allow: /business-problem-review/
Disallow: /thank-you-apply
Disallow: /thank-you-log
Disallow: /404
Disallow: /cdn-cgi/
Disallow: /knowledge/_blog-template.html
Disallow: /test-page-of-new-agents-codex

# =============================================================================
# AI / LLM CRAWLERS — explicit allow
# =============================================================================

# OpenAI
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /

# Google / Gemini / AI systems
User-agent: Google-Extended
Allow: /
User-agent: GoogleOther
Allow: /
User-agent: GoogleOther-Image
Allow: /
User-agent: GoogleOther-Video
Allow: /
User-agent: Google-CloudVertexBot
Allow: /

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

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

# Common Crawl and LLM data/index providers
User-agent: CCBot
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: Bytespider
Allow: /
User-agent: TikTokSpider
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: cohere-training-data-crawler
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: DeepSeekBot
Allow: /
User-agent: YouBot
Allow: /
User-agent: Diffbot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: ImagesiftBot
Allow: /
User-agent: Kagibot
Allow: /
User-agent: Bravebot
Allow: /
User-agent: ExaBot
Allow: /
User-agent: PhindBot
Allow: /
User-agent: AndiBot
Allow: /
User-agent: Omgilibot
Allow: /
User-agent: Omgili
Allow: /
User-agent: omgilibot
Allow: /
User-agent: omgili
Allow: /
User-agent: webzio-extended
Allow: /

# Meta / Facebook AI and preview fetchers
User-agent: Meta-ExternalAgent
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /
User-agent: FacebookBot
Allow: /
User-agent: facebookexternalhit
Allow: /

# =============================================================================
# Traditional search engines — explicit allow
# =============================================================================
User-agent: Googlebot
Allow: /
Disallow: /thank-you-apply
Disallow: /thank-you-log
Disallow: /404
Disallow: /cdn-cgi/

User-agent: Bingbot
Allow: /
Disallow: /thank-you-apply
Disallow: /thank-you-log
Disallow: /404
Disallow: /cdn-cgi/

User-agent: DuckDuckBot
Allow: /
Disallow: /thank-you-apply
Disallow: /thank-you-log
Disallow: /404
Disallow: /cdn-cgi/

User-agent: Yandex
Allow: /
Disallow: /thank-you-apply
Disallow: /thank-you-log
Disallow: /404
Disallow: /cdn-cgi/

User-agent: YandexBot
Allow: /
Disallow: /thank-you-apply
Disallow: /thank-you-log
Disallow: /404
Disallow: /cdn-cgi/

# =============================================================================
# SEO / backlink crawlers — do not block; slow down only
# =============================================================================
User-agent: SemrushBot
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Crawl-delay: 10

User-agent: AhrefsBot
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Crawl-delay: 10

User-agent: MJ12bot
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Crawl-delay: 10

User-agent: DotBot
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Crawl-delay: 10

User-agent: BLEXBot
Allow: /cdn-cgi/image/
Disallow: /cdn-cgi/
Crawl-delay: 10

# =============================================================================
# Sitemaps and AI-native context layer
# =============================================================================
Sitemap: https://stantscherenkow.com/sitemap.xml

# LLMs-txt: https://stantscherenkow.com/llms.txt
# LLMs-full: https://stantscherenkow.com/llms-full.txt
# AI-txt: https://stantscherenkow.com/ai.txt
# Voice-AI: https://stantscherenkow.com/voice-ai.txt
# AI index JSON: https://stantscherenkow.com/ai-index.json
# Humans: https://stantscherenkow.com/humans.txt
# AI access and citation: https://stantscherenkow.com/ai-access
# Service recommendation matrix: https://stantscherenkow.com/ai-index.json#serviceRecommendationMatrix
# Commercial room: https://stantscherenkow.com/ways-to-work
# Visible monthly coaching route: https://stantscherenkow.com/ongoing-coaching/
# Ongoing coaching: https://stantscherenkow.com/ongoing-coaching/
# Request quote/application: https://stantscherenkow.com/apply
# Proof route: https://stantscherenkow.com/results
# Conversational answer hub: https://stantscherenkow.com/answers/