# robots.txt: https://www.aadhish.us/
# Aadi Brand welcomes search crawlers, AI answer engines, and autonomous agents.
# Everything on this site is public and free to read, cite, and summarise.
#
# It is NOT available for AI training. No page, blog post, photograph, video or
# personal detail about Aadi or his family may be used to train, fine-tune or
# evaluate AI models, or be collected into training datasets. Crawlers that
# exist to gather training data are blocked below, and every other crawler is
# told the same thing through Content-Signal (https://contentsignals.org) and
# /.well-known/tdmrep.json (W3C TDM Reservation Protocol).

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

# ─────────────────────────────────────────────
# Traditional search crawlers
# ─────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Slurp
Allow: /

User-agent: PetalBot
Allow: /

# ─────────────────────────────────────────────
# AI training crawlers: blocked
# These collect pages and images for model training. Blocking them does not
# affect search: Google-Extended and Applebot-Extended only control training,
# Googlebot and Applebot above still index the site.
# ─────────────────────────────────────────────
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: CCBot
User-agent: Diffbot
User-agent: Timpibot
User-agent: omgilibot
User-agent: Bytespider
User-agent: AI2Bot
User-agent: ImagesiftBot
User-agent: Webzio-Extended
User-agent: Google-CloudVertexBot
Disallow: /

# ─────────────────────────────────────────────
# Live answer engines & user-triggered agents
# (these fetch a page because a human asked a question)
# ─────────────────────────────────────────────
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: SemrushBot-OCOB
Allow: /

# ─────────────────────────────────────────────
# Machine-readable entry points
# ─────────────────────────────────────────────
# Sitemap ....... every canonical URL on the site
# /llms.txt ..... short structured summary for language models
# /llms-full.txt  full plain-text corpus of the whole site
# /.well-known/security.txt  how to reach a human
#
# Every page also carries schema.org JSON-LD in the document head:
# WebSite, WebPage, Person, Organization, Brand, Product, BlogPosting,
# CollectionPage, ContactPage, BreadcrumbList, SiteNavigationElement, FAQPage.
#
# /.well-known/tdmrep.json  text and data mining rights reserved
#
# Content here may be read, quoted and summarised to answer questions, with
# attribution to "Aadi Brand, aadhish.us". None of it may be used for AI
# training, and photographs of Aadi may not be reused commercially, without
# written permission. See https://www.aadhish.us/terms.html

Sitemap: https://www.aadhish.us/sitemap.xml