User-agent: *
Allow: /

# Sitemap
Sitemap: https://finlingo.ai/sitemap.xml

# LLM/AI discovery files
# See https://llmstxt.org for the specification
Allow: /llms.txt
Allow: /llms-full.txt

# Explicitly allow AI search crawlers
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

# Allow static assets (fonts, CSS, JS) so Google can render pages properly
Allow: /_next/static/

# Disallow admin or private areas (intentionally blocked from indexing)
Disallow: /api/
Disallow: /admin/
Disallow: /private/
Disallow: /app/
Disallow: /auth/

# Disallow old/deprecated routes (all 301 redirect to / but block crawl budget waste)
Disallow: /leaderboard
Disallow: /lessons
Disallow: /dashboard
Disallow: /settings
Disallow: /transactions
Disallow: /chat
Disallow: /checkout
Disallow: /referral
Disallow: /practice
Disallow: /learn
Disallow: /search
Disallow: /test-sequencing
Disallow: /lesson-builder
Disallow: /page-backup

# Disallow functional/private pages that should not be indexed
Disallow: /reset-password
Disallow: /delete-my-data

# Disallow browser/OS config files — not content, waste crawl budget
Disallow: /browserconfig.xml
Disallow: /manifest.json
Disallow: /site.webmanifest

# Disallow tracking parameter variants — canonical is always the clean URL
# Prevents crawlers from indexing ?ref=, ?utm_*, etc. variants
Disallow: /*?ref=*
Disallow: /*?utm_source=*
Disallow: /*?utm_medium=*
Disallow: /*?utm_campaign=*
Disallow: /*?fbclid=*
Disallow: /*?gclid=*