# llms.txt for The Ko-Op (Last-Updated: 2025-10-01)
# Purpose: Set permissions for AI crawlers and LLM data usage.
 
# ---- Owner & Contact ----
Owner: The Ko-Op
Contact: psychedelictherapists@gmail.com
Website: https://psychedelictherapists.co
Sitemap: https://psychedelictherapists.co/sitemap.xml
 
# ---- Global Defaults (apply to all AI/LLM agents unless overridden) ----
User-agent: *
# Content usage:
Allow-Crawl: /blog/
Allow-Crawl: /for-therapists/
Allow-Crawl: /for-patients/
Disallow-Crawl: /admin/
Disallow-Crawl: /account/
Disallow-Crawl: /checkout/
Disallow-Crawl: /cart/
Disallow-Crawl: /wp-admin/
Disallow-Crawl: /privacy/ # may contain sensitive examples/requests
Disallow-Crawl: /terms/   # legal text not for model use
 
# Model training & dataset creation:
Disallow-Training: /      # Do NOT use any site content for training, fine-tuning, or datasets.
Disallow-Embedding: /     # Do NOT store long-term embeddings beyond transient indexing for search.
 
# Permitted lightweight uses:
Allow-Summarization: /blog/ ; max_output_chars=900 ; must_attribute=true ; link_back=true
Allow-Answering: /blog/ ; extractive_only=true ; snippet_length=<=100_words ; must_attribute=true
 
# Safety & privacy:
No-PII-Extraction: true
No-Health-Story-Mining: true   # Clinical/therapy narratives must not be harvested or profiled.
 
# Attribution & compliance:
Required-Attribution:
  name="The Ko-Op"
  url="https://psychedelictherapists.co"
  format="Source: The Ko-Op (linked)"
Commercial-Use: prohibited
Research-Use: noncommercial_only ; aggregate_only=true
 
# Access controls:
Rate-Limit: 5 requests/minute ; burst=10 ; crawl-delay=6
Respect-If-Modified-Since: true
Cache-Max-Age: 24h
 
# Review cadence:
Policy-Expires: 2026-10-01
 
# ---- Per-agent Overrides ----
# OpenAI
User-agent: GPTBot
Disallow-Crawl: /
Disallow-Training: /
Disallow-Embedding: /
 
# Google extended AI services
User-agent: Google-Extended
Disallow-Crawl: /
Disallow-Training: /
 
# Anthropic
User-agent: Claude-Web
Disallow-Crawl: /
Disallow-Training: /
 
# Perplexity
User-agent: PerplexityBot
Disallow-Crawl: /
Disallow-Training: /
 
# Common AI/data scrapers
User-agent: CCBot
Disallow-Crawl: /
Disallow-Training: /
 
User-agent: Applebot-Extended
Disallow-Crawl: /
Disallow-Training: /
 
User-agent: Amazonbot
Disallow-Crawl: /
Disallow-Training: /
 
User-agent: FacebookBot
Disallow-Crawl: /
Disallow-Training: /
 
User-agent: Bytespider
Disallow-Crawl: /
Disallow-Training: /
 
User-agent: Omgili
Disallow-Crawl: /
Disallow-Training: /
 
# ---- For Reader Notes ----
# This file governs AI/LLM usage. It supplements robots.txt (for general web crawlers).
# If you need limited permissions (e.g., a specific citation or quote), email the contact above.