# Content Signals (https://contentsignals.org/) — machine-readable statement of
# how this site's content may be used. haimaker.ai publishes technical content
# to be found, quoted, and learned from, so all three signals are yes.
#
#   search    = inclusion in a search index and links back to this site
#   ai-input  = use as input to an AI answer at query time (RAG, grounding)
#   ai-train  = use to train or fine-tune a generative AI model
#
# Signals are declared per group; each user-agent group below repeats them so a
# crawler matching a specific group still sees them.

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

# LLM Crawlers — explicit allow
User-agent: GPTBot
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: Google-Extended
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: ClaudeBot
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: 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: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Microsoft Copilot — explicit allow
User-agent: Bingbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

Sitemap: https://haimaker.ai/sitemap-index.xml
Sitemap: https://haimaker.ai/models/sitemap.xml
Sitemap: https://haimaker.ai/benchmarks/sitemap.xml