# BUI Awards 2026 — robots.txt
# Last updated: 2026-06-24
# Reference: https://www.robotstxt.org/

# ─────────────────────────────────────────────────────────────
# Default rule — allow all general-purpose crawlers
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=

# ─────────────────────────────────────────────────────────────
# Major search engines — explicit allow
# ─────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /

# ─────────────────────────────────────────────────────────────
# AI crawlers — training NOT authorised; real-time user fetch IS
# ─────────────────────────────────────────────────────────────

# OpenAI training — disallow
User-agent: GPTBot
Disallow: /

# OpenAI ChatGPT browsing on user request — allow
User-agent: ChatGPT-User
Allow: /

# OpenAI search index — allow
User-agent: OAI-SearchBot
Allow: /

# Google AI training — disallow
User-agent: Google-Extended
Disallow: /

# Anthropic — training disallow, real-time user fetch allow
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Common Crawl — disallow (primary AI training dataset source)
User-agent: CCBot
Disallow: /

# Perplexity — allow (user-prompted retrieval)
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence — training disallow, user agent allow
User-agent: Applebot-Extended
Disallow: /

User-agent: Applebot
Allow: /

# Meta AI training — disallow
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# ByteDance / TikTok — disallow
User-agent: Bytespider
Disallow: /

# Mistral — user fetch allow
User-agent: MistralAI-User
Allow: /

# Cohere — disallow
User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# ─────────────────────────────────────────────────────────────
# Discovery
# ─────────────────────────────────────────────────────────────
Sitemap: https://bui-awards.bui.co/sitemap.xml

# Machine-readable site index for LLMs and AI agents
# https://llmstxt.org
# Available at: https://bui-awards.bui.co/llms.txt