User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /?s=
Allow: /wp-admin/admin-ajax.php

# ChatGPT search
User-agent: OAI-SearchBot
Allow: /

# ChatGPT user-initiated browsing
User-agent: ChatGPT-User
Allow: /

# OpenAI training en plugins
User-agent: GPTBot
Allow: /

# OpenAI validatie ad-landingpages (ChatGPT Ads)
User-agent: OAI-AdsBot
Allow: /

# Perplexity search
User-agent: PerplexityBot
Allow: /

# Perplexity user-initiated browsing
User-agent: Perplexity-User
Allow: /

# Anthropic training en Claude analysis
User-agent: ClaudeBot
Allow: /

# Claude user-initiated browsing
User-agent: Claude-User
Allow: /

# Claude search
User-agent: Claude-SearchBot
Allow: /

# Anthropic legacy training-token
User-agent: anthropic-ai
Allow: /

# Anthropic legacy alias
User-agent: Claude-Web
Allow: /

# Mistral search-index (Le Chat / Vibe)
User-agent: MistralAI-Index
Allow: /

# Mistral user-initiated browsing
User-agent: MistralAI-User
Allow: /

# Google Search + AI Overviews + AI Mode
User-agent: Googlebot
Allow: /

# Gemini training en grounding
User-agent: Google-Extended
Allow: /

# Google AI research
User-agent: GoogleOther
Allow: /

# Google AI research (afbeeldingen)
User-agent: GoogleOther-Image
Allow: /

# Google AI research (video)
User-agent: GoogleOther-Video
Allow: /

# Vertex AI Agents (alleen op verzoek)
User-agent: Google-CloudVertexBot
Allow: /

# Google agentic browsing (Project Mariner)
User-agent: Google-Agent
Allow: /

# NotebookLM bron-ophalen op gebruikersverzoek
User-agent: Google-NotebookLM
Allow: /

# Google test-tools (Rich Result Test / URL-inspectie)
User-agent: Google-InspectionTool
Allow: /

# Bing + Microsoft Copilot
User-agent: bingbot
Allow: /

# Bing legacy alias
User-agent: MSNBot
Allow: /

# Bing legacy preview-alias
User-agent: BingPreview
Allow: /

# Siri en Spotlight
User-agent: Applebot
Allow: /

# Apple Intelligence training
User-agent: Applebot-Extended
Allow: /

# DuckDuckGo AI-assist answer engine
User-agent: DuckAssistBot
Allow: /

# You.com answer engine
User-agent: YouBot
Allow: /

# Kagi search en Kagi Assistant
User-agent: Kagibot
Allow: /

# Alexa en Amazon AI
User-agent: Amazonbot
Allow: /

# Amazon search (Alexa / Rufus)
User-agent: Amzn-SearchBot
Allow: /

# Meta AI training
User-agent: Meta-ExternalAgent
Allow: /

# Meta AI user-initiated ophalen
User-agent: Meta-ExternalFetcher
Allow: /

# Meta AI search-index
User-agent: meta-webindexer
Allow: /

# Petal / Huawei search
User-agent: PetalBot
Allow: /

# Common Crawl (publieke trainingsdata)
User-agent: CCBot
Allow: /

# Allen Institute for AI (onderzoek)
User-agent: AI2Bot
Allow: /

# Allen Institute Dolma trainings-corpus
User-agent: Ai2Bot-Dolma
Allow: /

# Cohere training (gedocumenteerd)
User-agent: cohere-training-data-crawler
Allow: /

# Social link-preview (geen AI-crawler)
User-agent: facebookexternalhit
Allow: /

# ByteDance / Doubao / TikTok AI: alleen profiel + sitemap
User-agent: Bytespider
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /wp-sitemap.xml
Allow: /wp-sitemap-
Disallow: /

# Data-aggregators en scrapers: alleen profiel + sitemap
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Timpibot
User-agent: Webzio-Extended
User-agent: PanguBot
User-agent: VelenPublicWebCrawler
User-agent: cohere-ai
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /wp-sitemap.xml
Allow: /wp-sitemap-
Disallow: /

Sitemap: https://www.citeerbaar.nl/wp-sitemap.xml