# irahulsoni.com · © 2026 Rahul Soni · Only4Values. All rights reserved.
#
# Policy: search engines and AI search / answer engines are welcome to read this site,
# answer questions from it, and cite and link to it. AI training, dataset building,
# bulk scraping, copying and cloning are not permitted (see /terms/ and /llms.txt).
# A plain-text profile for AI assistants and agents: https://irahulsoni.com/llms.txt
# The full version, in one file: https://irahulsoni.com/llms-full.txt
#
# Content Signals (Content Signals Policy, CC0, https://contentsignals.org/):
#   search   = building a search index and showing links and short excerpts
#   ai-input = feeding content into an AI model to answer a question in real time
#              (grounding, retrieval), with credit and a link back
#   ai-train = training or fine-tuning AI models
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF RIGHTS
# UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT AND RELATED
# RIGHTS IN THE DIGITAL SINGLE MARKET.

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

# AI training crawlers and dataset builders: not permitted.
# (Listed before the welcome group so parsers that match names loosely still read Applebot-Extended as blocked.)
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: GoogleOther
User-agent: Applebot-Extended
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: MistralAI-Training
User-agent: Diffbot
User-agent: omgili
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: Timpibot
User-agent: YouBot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: PanguBot
User-agent: KimiBot
User-agent: Baiduspider
User-agent: PetalBot
User-agent: AwarioSmartBot
User-agent: AwarioRssBot
User-agent: QualifiedBot
User-agent: Cotoyogi
User-agent: ICC-Crawler
User-agent: atlassian-bot
User-agent: FishBot
User-agent: BorderxBot
User-agent: NavuBot
User-agent: SemrushBot-SWA
User-agent: WARDBot
User-agent: magpie-crawler
User-agent: CitibotSiteCrawler
Disallow: /

# Search engines, AI search engines and user-requested AI fetchers: welcome.
# (Named so the policy is explicit; a bot that finds its own name ignores the * group.)
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: MistralAI-Index
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: meta-externalfetcher
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

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