# llm.txt for lief.ai
# Last-Updated: 2025-10-04
# Owner: Lief AI (https://lief.ai)
# Contact: team@lief.ai
# Purpose: Declare permissions for AI/LLM indexing, summarization, and limited training.
# Canonical-Domain: https://lief.ai
# Sitemap: https://lief.ai/sitemap.xml
############################
# GLOBAL POLICY FOR AI/LLMs
############################
# Summary:
# We encourage discovery, summarization, and responsible model training on our public content.
# Please respect our rate limits and avoid crawling private or transactional pages.
[policy]
allow_browse: true
allow_snippets: true
allow_training: true               # :white_check_mark: Training allowed on public pages
allow_indexing: true
allow_rag_use: true                # OK for retrieval-augmented generation (RAG)
require_attribution: true          # Please include a link to https://lief.ai when summarizing or citing content
cache_hours: 168                   # 7 days
rate_limit_rps: 1
respect_noindex: true
respect_noarchive: true
#####################################
# PATH RULES
#####################################
# Public content is open.
# The following areas are private or dynamic — do not crawl or index.
[paths]
disallow:
  - /account
  - /admin
  - /api
  - /auth
  - /cart
  - /checkout
  - /orders
  - /profile
  - /dashboard
  - /download
  - /wp-admin
  - /wp-login.php
###################################
# AGENT-SPECIFIC NOTES
###################################
[user-agent "GPTBot"]
allow_training: true
note: "You may use lief.ai public pages for model training and to surface answers in ChatGPT. Please attribute 'Lief AI (lief.ai)'."
[user-agent "ChatGPT-User"]
allow_browse: true
note: "Real-time retrieval allowed for user queries with attribution."
[user-agent "PerplexityBot"]
allow_training: true
note: "Allowed for indexing, summarization, and citations in answers."
[user-agent "Google-Extended"]
allow_training: true
note: "Allowed for AI model training and ranking within AI overviews."
[user-agent "ClaudeBot"]
allow_training: true
[user-agent "CCBot"]
allow_training: true
note: "Public pages only; respect rate limits."
########################################
# ATTRIBUTION & LICENSE
########################################
[attribution]
site_name: "Lief AI"
url: "https://lief.ai"
license: "CC BY 4.0-like (attribution required)"
permitted_use: "Training, summarization, and citation of public content with attribution."
prohibited_use: "Use of private, personal, or confidential data; scraping rate abuse."
# End of llm.txt