# ─────────────────────────────────────────────────────────────────────
# Academee — robots.txt
# AI crawlers explicitly allowed for Generative Engine Optimization.
# Israeli online tutor marketplace. Open marketing pages; private app routes blocked.
# ─────────────────────────────────────────────────────────────────────

# ── AI / LLM crawlers — explicitly allowed for AI-answer citation ──
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# ── Default policy ──
User-agent: *
Allow: /

# Block private/admin areas
Disallow: /admin/
Disallow: /checkout
Disallow: /api/
Disallow: /personal-area
Disallow: /mentor/
Disallow: /lessons/
Disallow: /calendar/

# Block legacy duplicate URLs
Disallow: /index

# Tracking-param duplicates (?utm_ / ?fbclid= / ?gclid=) are NOT blocked here.
# Every page emits a clean rel=canonical (verified), so Google consolidates the
# param variants into the canonical URL on its own. Blocking them in robots.txt
# only produced "Indexed, though blocked by robots.txt" warnings in GSC and
# stopped Google from reading the canonical — so shared social/ads links passed
# no equity to the real page. Leaving them crawlable is the correct, SEO-positive
# setup (Google's own recommendation for parameter de-duplication).

# Sitemap
Sitemap: https://www.academee.co.il/sitemap.xml