# robots.txt for kumisearch.com
# Last updated: August 2026
# Review quarterly — new AI crawlers appear several times a year.

# Default: allow all standard crawlers (Google, Bing, etc.)
User-agent: *
Allow: /

# --- Explicit entries for the two crawlers that matter most, for clarity ---
# (Already covered by the wildcard above — listed explicitly so nobody editing
# this file later mistakes the AI-specific entries below as the only ones allowed.)

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# --- AI Search & Retrieval Bots ---
# These power live citations in AI answers (ChatGPT Search, Perplexity Answers, etc.)
# Blocking these is what actually removes a site from AI-generated answers.

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: DuckAssistBot
Allow: /

# --- AI User-Triggered Fetch Agents ---
# Activate when a person directly asks an AI assistant to open a specific page.

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

# --- AI Training Crawlers ---
# Build long-term model knowledge rather than live citations.
# Allowed here since this is public marketing content meant to build authority —
# blocking these would only reduce future visibility with no real benefit.

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: CCBot
Allow: /

Sitemap: https://www.kumisearch.com/sitemap.xml