# robots.txt for ainewsforall.com
# We WANT to be found and cited by search engines and AI assistants, so every crawler below is allowed.
# Only the on-site search results page is excluded (it has no unique content).

# --- Search engines ---
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: YandexBot
User-agent: Baiduspider

# --- AI search / answer engines (index pages so assistants can cite us) ---
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: DuckAssistBot

# --- AI assistants fetching a page because a person asked ---
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Perplexity-User
User-agent: MistralAI-User
User-agent: Meta-ExternalFetcher

# --- AI model training (allowed: helps models learn the site and the brand) ---
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: CCBot
User-agent: cohere-ai

# --- Everyone else ---
User-agent: *
Allow: /
Disallow: /search/

Sitemap: https://ainewsforall.com/sitemap.xml