# ai.txt — AI crawler & model usage policy for ProgComm
# Generated on 2025-08-25
# Spec: Informal/experimental; mirrors common directives used by AI crawlers.
# Place at: https://progcomm.ai/ai.txt

[site]
name = "ProgComm"
url = "https://progcomm.ai"
owner = "ProgComm"
contact = "info@progcomm.com"

[policy]
# High-level intent:
# - Allow AI agents to index the public website for search and snippets.
# - Disallow using our content to train or fine-tune foundation models without a written agreement.
# - Permit brief previews/snippets with attribution and a link back.
allow_search_indexing = true
allow_snippets_previews = true
require_attribution_link = true
allow_model_training = false
allow_dataset_redistribution = false

[allowed-paths]
# Public marketing pages may be indexed/snippet-rendered.
paths = [
  "/",
  "/og.png",
  "/ProgCommHeadLogo.png"
]

[disallowed-paths]
# Block model-training or dataset harvesting across the board.
paths = [
  "/private",
  "/api",
  "/assets/raw",
  "/static/export",
  "/admin",
  "/dashboard"
]

[crawlers]
# Explicit crawler guidance. (Crawlers should also honor robots.txt.)
# Search/snippet bots — ALLOW (no training):
"Google-Extended" = "Allow: snippets only; Disallow: training"
"AppleBot-Extended" = "Allow: snippets only; Disallow: training"
"Bingbot" = "Allow: indexing/snippets"
# Foundation/training-oriented crawlers — DISALLOW unless contracted:
"GPTBot" = "Disallow: model training; Allow: robots-compliant crawling for safety review"
"GPTBot-Image" = "Disallow: training"
"CCBot" = "Disallow: training"
"Claude-Web" = "Disallow: training"
"FacebookBot" = "Disallow: training"
"PerplexityBot" = "Disallow: training"
"YouBot" = "Disallow: training"
"Amazonbot" = "Disallow: training"

[licensing]
# Content license for AI uses beyond fair-use snippets:
license = "All rights reserved. Separate license required for training/fine-tuning."
how_to_request = "Email info@progcomm.com with subject 'AI Training License Request'."

[enforcement]
violation_contact = "info@progcomm.com"
# If you operate a crawler, cache or LLM using our content beyond the allowances above,
# you agree to cease such activity upon our notice.