# LLMs Policy File for Ingenia (non-standard, advisory)
# Location: /llms.txt
# Docs: inspired by community proposals for AI crawling governance

version: 1.0
site: https://ingenia.la
owner: Ingenia
contact:  compliance@ingenia.la
last_updated: 2025-10-29

# Global policy for model training/usage of public content
# POLICY OPTIONS: allow | disallow | conditional
#   - allow: Permite uso completo para entrenamiento de modelos
#   - disallow: Bloquea todo uso para entrenamiento de modelos
#   - conditional: Permite con condiciones especificadas abajo
policy: conditional

# LICENSE OPTIONS:
#   - CC BY 4.0: Atribución (permite uso comercial)
#   - CC BY-NC 4.0: Atribución, No comercial (recomendado)
#   - CC BY-SA 4.0: Atribución, Compartir igual
#   - CC BY-ND 4.0: Atribución, Sin derivados
#   - CC BY-NC-SA 4.0: Atribución, No comercial, Compartir igual
#   - CC BY-NC-ND 4.0: Atribución, No comercial, Sin derivados
#   - CC0 1.0: Dominio público
#   - All Rights Reserved: Todos los derechos reservados
license: CC BY-NC 4.0

# ATTRIBUTION OPTIONS: required | optional | not required
#   - required: Atribución obligatoria
#   - optional: Atribución recomendada pero no obligatoria
#   - not required: No se requiere atribución
attribution: required

# High-level conditions for AI agents
conditions:
  - Respect robots.txt and user-agent specific rules (e.g., GPTBot, Google-Extended, CCBot)
  - Provide clear attribution to Ingenia with a link when using excerpts
  - Do not use content for commercial model training without permission
  - Honor per-path allow/disallow below

# Suggested rate limits for automated agents
rate_limit: 1 rps
concurrency: 1

# Preferred discovery endpoints
sitemaps:
  - https://ingenia.la/robots.txt

# Markdown content endpoints for AI bots and crawlers
# These endpoints serve plain markdown versions of important pages
content_endpoints:
  # Legal pages
  - /api/content/ai-content-policy.md?locale=en
  - /api/content/ai-content-policy.md?locale=es
  - /api/content/privacy-policy.md?locale=en
  - /api/content/privacy-policy.md?locale=es
  - /api/content/cookies-policy.md?locale=en
  - /api/content/cookies-policy.md?locale=es
  - /api/content/ethics-code.md?locale=en
  - /api/content/ethics-code.md?locale=es
  
  # Main pages
  - /api/content/solutions.md?locale=en
  - /api/content/solutions.md?locale=es
  - /api/content/solutions/vision.md?locale=en
  - /api/content/solutions/vision.md?locale=es
  - /api/content/solutions/creation.md?locale=en
  - /api/content/solutions/creation.md?locale=es
  - /api/content/solutions/adoption.md?locale=en
  - /api/content/solutions/adoption.md?locale=es
  - /api/content/solutions/ai-powered-solutions.md?locale=en
  - /api/content/solutions/ai-powered-solutions.md?locale=es
  - /api/content/about-us.md?locale=en
  - /api/content/about-us.md?locale=es
  - /api/content/case-studies.md?locale=en
  - /api/content/case-studies.md?locale=es
  - /api/content/contact-us.md?locale=en
  - /api/content/contact-us.md?locale=es
  - /api/content/techreport.md?locale=en
  - /api/content/techreport.md?locale=es
  - /api/content/venture-program.md?locale=en
  - /api/content/venture-program.md?locale=es

# Canonical public pages (localized). Note: dynamic locales under /[locale]
include_paths:
  # Localized app root
  - /en
  - /es

  # Key sections (depending on locale routing)
  - /en/about-us
  - /es/nosotros
  - /en/solutions
  - /es/soluciones
  - /en/community
  - /es/comunidad
  - /en/contact-us
  - /es/contacto
  - /en/case-studies
  - /es/case-studies

  # Tech report landing mentioned by marketing
  - /en/techreport
  - /es/techreport

# Public static assets (representative patterns)
assets_allow:
  # Favicons & PWA
  - /favicon.ico
  - /favicon.svg
  - /icons/*
  - /web-app-manifest-192x192.png
  - /web-app-manifest-512x512.png

  # Images and media used across pages
  - /images/*
  - /images/home/*
  - /images/aboutUs/*
  - /images/solutions/*
  - /images/venture/*
  - /sliders/*
  - /logos/*
  - /home/*

# Explicit asset examples from this deployment (non-exhaustive)
assets_examples:
  - /images/aboutUs/about-us.webp
  - /images/home/hero_01.png
  - /images/home/hero_02.png
  - /images/home/hero_03.png
  - /images/home/we-are-unique.jpg
  - /images/solutions/vision/*
  - /images/solutions/adoption/*
  - /images/solutions/creation/*
  - /images/solutions/aiPoweredSolutions/*
  - /images/venture/*
  - /icons/arrow_outward.svg
  - /icons/whatsapp-map.svg
  - /logos/ingenia.svg

# Programmatic or sensitive endpoints to exclude
# (APIs, forms processing, internal services, admin areas)
# Note: /api/content/*.md endpoints are allowed above for AI bots
disallow:
  - /api/contact-us/*
  - /api/join-us/*
  - /api/venture/*
  - /api/revalidate/*
  - /api/tags/*
  - /api/geo/*
  - /api/case-studies/*
  - /en/api/*
  - /es/api/*
  - /wp-admin/*
  - /private/*
  - /admin/*
  - /draft/*
  - /uploads/*
  - /storage/*
  - /files/*
  - /media/*
  - /tmp/*
  - /backups/*
  - /graphql*
  - /wp-json/*
  - /auth/*
  - /login/*
  - /logout/*
  - /register/*
  - /user/*
  - /profile/*
  - /sessions/*
  - /tokens/*
  - /cms/*
  - /headless/*
  - /preview/*
  - /drafts/*
  - /internal/*
  - /system/*

# Forms endpoints (human use only; do not crawl/ingest submissions)
# These are already listed in disallow above

# Internationalization notes
locales:
  default: es
  supported:
    - en
    - es

# Preferred citation
citation:
  name: Ingenia
  url: https://ingenia.la
  policy_url: https://ingenia.la/legal/ai-content-policy

# Notes for AI crawlers
notes:
  - This file is advisory and complements robots.txt. Some user-agents may not yet support llms.txt.
  - If you operate an AI crawler, please send questions to  compliance@ingenia.la.
  - For partnership or licensed dataset access, contact growthoperations@ingenia.la.

# End of file