# robots.txt for joshua.olunlade.com
# Search engines and AI search tools: welcome.
# Crawlers that collect pages to train AI models: not permitted.
# Rights are reserved. See https://joshua.olunlade.com/ai-policy/

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# ─── AI search and answer tools (allowed) ─────────────────────────────────────
# OpenAI: Finds pages to show in ChatGPT search.
User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# OpenAI: Opens a page when a ChatGPT user asks about it.
User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Anthropic: Finds pages for Claude's search results.
User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Anthropic: Opens a page when a Claude user asks about it.
User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Perplexity: Finds pages to cite in Perplexity answers.
User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Perplexity: Opens a page when a Perplexity user asks about it.
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# DuckDuckGo: Fetches pages for DuckDuckGo's AI-assisted answers.
User-agent: DuckAssistBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# ─── Crawlers that collect pages to train AI models (not permitted) ───────────
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Timpibot
User-agent: AI2Bot
Disallow: /

Sitemap: https://joshua.olunlade.com/sitemap.xml