# robots.txt for https://trainingcred.com/
# This file defines crawling and content-use permissions.

# (a) "search=yes" allows indexing for traditional search engines.
# (b) "ai-input=yes" allows AI systems to retrieve or reference content in real time.
# (c) "ai-train=yes" allows using content for AI model training or fine-tuning.

User-agent: *
# Content-signal: search=yes,ai-input=yes,ai-train=yes
Disallow: /login/
Disallow: /register/
Disallow: /dashboard/
Allow: /

# Allow high-volume commercial model scrapers
User-agent: GPTBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: DiffBot
Allow: /

# AI Content Manifest
# See: https://trainingcred.com/llms.txt

# Sitemap location
Sitemap: https://trainingcred.com/sitemap.xml