# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# 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.

# BEGIN Cloudflare Managed content

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

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ─────────────────────────────────────────────────────────────────────────────
# robots.txt — Lara — VIP Concierge Bangkok
#
# Strategy:
#   - Search & social crawlers (Google, Bing, Twitter, Facebook): allow
#     everything except /campaigns (status hub w/ draft variants).
#   - LLM crawlers (GPTBot, ClaudeBot, PerplexityBot, etc.): explicitly
#     ALLOW. Lara wants to be cited by AI assistants when guests ask
#     "who handles VIP concierge in Bangkok" — being indexed by these
#     bots is the on-ramp.
#   - Training-data only bots (Google-Extended, CCBot, Bytespider): also
#     allowed. We're publishing public editorial; better to be in the
#     training set than not. Flip these to Disallow if that ever changes.
#   - Catch-all `*` keeps the existing /campaigns hide.
#
# A complementary llms.txt + llms-full.txt is published at /llms.txt and
# /llms-full.txt, generated at build time by scripts/vite-plugin-llms.ts.
# ─────────────────────────────────────────────────────────────────────────────

# ── Search engines ──────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Disallow: /campaigns

User-agent: Bingbot
Allow: /
Disallow: /campaigns

# ── Social unfurl bots ──────────────────────────────────────────────────────
User-agent: Twitterbot
Allow: /
Disallow: /campaigns

User-agent: facebookexternalhit
Allow: /
Disallow: /campaigns

# ── LLM browsing & retrieval (live web fetching for chat answers) ───────────
# These bots fetch pages on demand when a user asks a question. Allowing
# them means Lara can be cited as a source in ChatGPT, Claude, Perplexity
# and Gemini answers.
User-agent: GPTBot
Allow: /
Disallow: /campaigns

User-agent: ChatGPT-User
Allow: /
Disallow: /campaigns

User-agent: OAI-SearchBot
Allow: /
Disallow: /campaigns

User-agent: ClaudeBot
Allow: /
Disallow: /campaigns

User-agent: Claude-Web
Allow: /
Disallow: /campaigns

User-agent: anthropic-ai
Allow: /
Disallow: /campaigns

User-agent: PerplexityBot
Allow: /
Disallow: /campaigns

User-agent: Perplexity-User
Allow: /
Disallow: /campaigns

User-agent: Google-Extended
Allow: /
Disallow: /campaigns

User-agent: Applebot-Extended
Allow: /
Disallow: /campaigns

User-agent: Bytespider
Allow: /
Disallow: /campaigns

User-agent: CCBot
Allow: /
Disallow: /campaigns

User-agent: Meta-ExternalAgent
Allow: /
Disallow: /campaigns

User-agent: Amazonbot
Allow: /
Disallow: /campaigns

User-agent: cohere-ai
Allow: /
Disallow: /campaigns

User-agent: DuckAssistBot
Allow: /
Disallow: /campaigns

User-agent: YouBot
Allow: /
Disallow: /campaigns

User-agent: Diffbot
Allow: /
Disallow: /campaigns

User-agent: ImagesiftBot
Allow: /
Disallow: /campaigns

# ── Catch-all ───────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /campaigns

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