# robots.txt for https://kaamcam.com
# Field Service Management Software by Four Cents

# Allow all search engine bots
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# AI crawlers and assistants: explicitly welcomed
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: Googlebot-AI
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Default rule for all other bots
User-agent: *
Allow: /

# Block API endpoints and build assets
Disallow: /api/
Disallow: /assets/

# NOTE ON /fr/ AND /es/ (deliberately NOT disallowed yet).
#
# Those prefixes serve English content, so each page now carries
# noindex + a canonical pointing at its English original (see
# server/seoMeta.ts). They were absorbing roughly a third of crawl budget:
# ~1,291 unique /fr/ + /es/ URLs crawled in a 14-day window vs 2,470
# English URLs.
#
# Disallowing them HERE would be counterproductive right now: a blocked URL
# cannot be re-crawled, so Google would never see the noindex or the new
# canonical, and the duplicates would linger in the index unconsolidated.
# Correct sequence is noindex/canonical first, let it propagate, then block.
#
# FOLLOW-UP: once GSC shows the /fr/ and /es/ URLs dropped or consolidated
# (recheck ~4 weeks after 2026-07-24), add:
#   Disallow: /fr/
#   Disallow: /es/
# to reclaim the crawl budget permanently.

# Sitemap index + per-language sitemaps.
# ES/FR sitemaps list ONLY the translated, indexable money-page route types
# (salary/cost/license/workers-comp by state + cost-by-city), each with a
# full en/es/fr hreflang cluster. Noindexed ES/FR pages (everything else)
# are excluded, so nothing here contradicts a per-page noindex tag.
Sitemap: https://kaamcam.com/sitemap.xml
Sitemap: https://kaamcam.com/sitemap-en.xml
Sitemap: https://kaamcam.com/sitemap-es.xml
Sitemap: https://kaamcam.com/sitemap-fr.xml
Sitemap: https://kaamcam.com/sitemap-video.xml
Sitemap: https://kaamcam.com/rss.xml

# LLM-friendly content summary
# Short version: https://kaamcam.com/llms.txt
# Full version: https://kaamcam.com/llms-full.txt