# ─────────────────────────────────────────────────────────────────────────────
#  robots.txt
# ─────────────────────────────────────────────────────────────────────────────
#  Nothing is blocked. The brief's whole thesis is that this content should be
#  crawled, understood and cited. A site that exists to be a knowledge layer
#  has no reason to disallow retrieval.
#
#  Search and internal utility endpoints are allowed too — /search/ is a real
#  page with a real URL and its results are legitimate landing pages.
#
#  NOTE ON llms.txt (§37 of the brief): no llms.txt is published. The brief is
#  explicit that it is not a substitute for crawlability, structure, evidence
#  or authority. Crawl budget here is trivial, so no crawl-delay is set.
# ─────────────────────────────────────────────────────────────────────────────

User-agent: *
Allow: /

# AI retrieval and answer systems — explicitly welcomed, not merely tolerated.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bingbot
Allow: /

# Sitemap index (§23). Children: /sitemaps/pages.xml, articles.xml, fabrics.xml,
# countries.xml, glossary.xml, research.xml, datasets.xml, manufacturers.xml
Sitemap: https://kubramal.com/sitemap.xml