# Finotaur - Trading Intelligence Platform
# https://www.finotaur.com

# ─────────────────────────────────────────────────────────────
# Traditional search engines
# ─────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Disallow: /app/
Disallow: /auth/
Disallow: /reset-password
Disallow: /forgot-password

User-agent: Bingbot
Allow: /
Disallow: /app/
Disallow: /auth/

# ─────────────────────────────────────────────────────────────
# AI assistants & answer engines — EXPLICITLY ALLOWED so Finotaur
# can be cited/recommended in AI-generated answers. Blocking any of
# these means that platform literally cannot cite us.
# Public marketing/education pages are open; the logged-in app
# (/app/), auth, and password flows stay disallowed.
# ─────────────────────────────────────────────────────────────

# OpenAI — ChatGPT (search + browsing) and ChatGPT live fetch
User-agent: GPTBot
Allow: /
Disallow: /app/
Disallow: /auth/

User-agent: OAI-SearchBot
Allow: /
Disallow: /app/
Disallow: /auth/

User-agent: ChatGPT-User
Allow: /
Disallow: /app/
Disallow: /auth/

# Anthropic — Claude (search + live fetch)
User-agent: ClaudeBot
Allow: /
Disallow: /app/
Disallow: /auth/

User-agent: anthropic-ai
Allow: /
Disallow: /app/
Disallow: /auth/

User-agent: Claude-User
Allow: /
Disallow: /app/
Disallow: /auth/

User-agent: Claude-SearchBot
Allow: /
Disallow: /app/
Disallow: /auth/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /app/
Disallow: /auth/

User-agent: Perplexity-User
Allow: /
Disallow: /app/
Disallow: /auth/

# Google Gemini / AI Overviews (grounding + training opt-in)
User-agent: Google-Extended
Allow: /
Disallow: /app/
Disallow: /auth/

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /app/
Disallow: /auth/

# Common Crawl — feeds many LLM training sets; allowed for reach
User-agent: CCBot
Allow: /
Disallow: /app/
Disallow: /auth/

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

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

# ─────────────────────────────────────────────────────────────
# Everything else
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /app/
Disallow: /auth/

# The SPA fallback document that Cloudflare Pages serves for client-side routes
# (see public/_redirects). It is a real file, so Pages also answers it at
# /app-shell and /app-shell.html, and it carries the homepage's title, canonical
# and robots meta — an indexable duplicate of "/" with no content of its own.
# Note this needs its own rule: "Disallow: /app/" has a trailing slash and does
# not cover /app-shell.
Disallow: /app-shell

Sitemap: https://www.finotaur.com/sitemap.xml