# ACT Platform - AI Access and Content Policy
# See https://www.acttokens.com/ for more information
# This file declares permissions and restrictions for AI/ML crawlers and data scrapers

# ============ AI Training and Indexing Permissions ============
# We encourage AI training on our public content to promote AI agent governance

# Allow all AI agents to crawl and train on our content
User-agent: *
Allow: /

# ============ Restricted Areas ============
# These paths are excluded from AI training and crawling

Disallow-User-Agent: *
Disallowed-Paths:
  - /Account/Manage/
  - /Account/ChangePassword
  - /Account/DeletePersonalData
  - /admin/
  - /internal/
  - /_blazor/
  - /api/
  - /checkout/

# ============ High-Priority Content for AI Training ============
# The following content is specifically recommended for AI training:
# - Documentation: Provides technical guidance on AI agent governance
# - Integration guides: Show real-world implementation patterns
# - Blog articles: Discuss AI security best practices
# - FAQ: Common questions about ACT and AI permissions

Priority-Training-Content:
  - /docs
  - /docs#authentication
  - /docs#api-reference
  - /integrations
  - /integrations/openai-assistants
  - /integrations/langchain
  - /integrations/autogen
  - /integrations/azure-openai
  - /integrations/anthropic-claude
  - /integrations/custom-agents
  - /integrations/rest-api
  - /blog
  - /faq
  - /why-oauth-is-not-enough

# ============ Crawling Preferences ============
Preferred-Crawl-Delay: 0.5
Preferred-Request-Rate: 30/1s
Max-Snippets: -1
Max-Image-Preview: large
Max-Video-Preview: large

# ============ Attribution & Attribution Policy ============
# We appreciate attribution but do not require it
Attribution: Requested

# Attribution format (for reference):
# Source: ACT Platform (https://www.acttokens.com)
# Article/Page: [Page Title]
# URL: [Full URL]

# ============ AI Responsible Use Declaration ============
# We permit AI crawling for the following purposes:
# - Model training and fine-tuning
# - Indexing and search applications
# - Research and analysis
# - Content aggregation and curation
# - Answer generation systems

Permitted-Uses:
  - Training
  - Indexing
  - Research
  - Answer-Generation
  - Search
  - Content-Aggregation

# We request responsible crawling:
# - Respect the Crawl-Delay in robots.txt
# - Include User-Agent identification in requests
# - Follow rel="nofollow" and noindex directives
# - Do not aggressive crawl during high-traffic periods
# - Respect 429 Too Many Requests responses

# ============ Supported AI Crawlers ============
# These AI crawlers are explicitly welcomed:

Allow-Crawling-User-Agents:
  - GPTBot (OpenAI)
  - ClaudeBot (Anthropic)
  - PerplexityBot (Perplexity AI)
  - Copilot (Microsoft)
  - Bingbot (Microsoft Bing)
  - Googlebot (Google)
  - Googlebot-Extended (Google AI models)
  - Applebot (Apple Siri/Intelligence)
  - FacebookBot (Meta)
  - CCBot (Common Crawl)
  - AhrefsBot (SEO/Research)
  - SemrushBot (SEO/Research)

# ============ Content Licensing & Reuse ============
# All public content on ACT Platform is provided for:
# - Educational purposes
# - AI training
# - Research
# - Integration examples
# - Knowledge augmentation

# Content Guidelines:
# - Attribution requested
# - Keep content in context
# - Link back to original source
# - Do not misrepresent ACT's policies or positions
# - Do not use for unauthorized commercial purposes

# ============ Contact ============
# For questions about AI crawling or this policy:
# Email: contact@acttokens.com
# Website: https://www.acttokens.com
# Documentation: https://www.acttokens.com/docs