# Decision D-V2-9: search and AI-answer engines allowed, training crawlers blocked.
# Matches Content-Signal: ai-train=no, search=yes, ai-input=yes.
# /cv/, /now/, /rights/, /presentations/ and /feed.xml are kept out of search with a noindex directive
# (meta tag and X-Robots-Tag header), not with a Disallow: a blocked URL can still be listed,
# and blocking it would stop the crawler reading the noindex.
# Refresh against https://github.com/ai-robots-txt/ai.robots.txt (195 agents on 2026-10-23) and the vendors' pages.
# Content-Usage follows the IETF AI-preferences Internet-Drafts (draft-ietf-aipref-vocab-08, -attach-05):
# drafts, not yet a standard; parsers that do not know the line ignore it.

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

# --- Training / dataset crawlers: blocked -------------------------------------
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: omgilibot
User-agent: omgili
User-agent: webzio-extended
User-agent: Webzio-Extended
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: AI2Bot
User-agent: Kangaroo Bot
User-agent: PanguBot
User-agent: Timpibot
User-agent: Bravebot
User-agent: SemrushBot-OCOB
User-agent: VelenPublicWebCrawler
User-agent: Sidetrade indexer bot
User-agent: Crawlspace
User-agent: TikTokSpider
User-agent: iaskspider
User-agent: ICC-Crawler
User-agent: PetalBot
# added 2026-10-23 (vendor pages + ai.robots.txt)
User-agent: MistralAI-Training
User-agent: Ai2Bot-Dolma
User-agent: aiHitBot
User-agent: Brightbot
User-agent: ChatGLM-Spider
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: DeepSeekBot
User-agent: DoubaoBot
User-agent: ERNIEBot
User-agent: Factset_spyderbot
User-agent: FriendlyCrawler
User-agent: Hunyuan
User-agent: ISSCyberRiskCrawler
User-agent: KimiBot
User-agent: LAIONDownloader
User-agent: laion-huggingface-processor
User-agent: MoonshotBot
User-agent: QwenBot
User-agent: SBIntuitionsBot
User-agent: xAI-Grok
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: YiBot
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: imageSpider
User-agent: WARDBot
User-agent: Awario
User-agent: Panscient
User-agent: panscient.com
User-agent: AgentDataBot
User-agent: EchoboxBot
User-agent: LCC
User-agent: Scrapy
Disallow: /

# --- Answer / search engines: allowed on purpose ------------------------------
# Googlebot, Bingbot, Applebot, DuckDuckBot, OAI-SearchBot, ChatGPT-User,
# Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, DuckAssistBot,
# MistralAI-Index, MistralAI-User, Amzn-SearchBot, Amzn-User, meta-webindexer,
# YouBot — covered by "User-agent: *" above.
# Blocking these would remove citations of your work from AI answers.

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