# robots.txt for https://kognity.com/
# Last updated: 2025-10-28
# Maintained by: Kognity AB
# Purpose: Control search indexing and AI crawler access

# =========================
# 📘 Standard web crawlers
# =========================

User-agent: *
Allow: /
Sitemap: https://kognity.com/sitemap.xml

# =========================
# 🤖 AI / LLM crawlers
# =========================
# This section clarifies how generative AI and large language model crawlers may access Kognity content.

# OpenAI (ChatGPT / GPTBot)
User-agent: GPTBot
Disallow: /app/
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Disallow: /app/
Allow: /

# Google Extended (Bard / Gemini data)
User-agent: Google-Extended
Disallow: /app/
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Disallow: /app/
Allow: /

# Common Crawl
User-agent: CCBot
Disallow: /app/
Allow: /

# Facebook AI Research
User-agent: FacebookBot
Disallow: /app/
Allow: /

# =========================
# 📄 LLMs metadata pointer
# =========================
# Points AI crawlers to Kognity's llms.txt for usage policy and attribution guidelines.
LLMs: https://kognity.com/llms.txt

# =========================
# 🛡️ Private / non-public sections
# =========================
# Internal platform areas not intended for indexing or AI ingestion
Disallow: /login
Disallow: /app/
Disallow: /dashboard/
Disallow: /admin/
Disallow: /user/
Disallow: /privacy/internal/
Disallow: /wp-admin/