# llms.txt for allied.com — v0.4
# Policy: Retrieval OK for public content; opt out of model training.
# Note: Do NOT block query parameters; site filters rely on them.
# Exception: Block /files/*

User-agent: *
Allow: /
Allow: /moving-companies/
Allow: /household-moving-company/
Allow: /local/
Allow: /international-moving-company/
Allow: /moving-resources/
Allow: /corporate-relocation-services/
Allow: /about-allied
Allow: /blog/
# Exception
Disallow: /files/*

Use-Training: disallow
Use-Retrieval: allow
Use-Evaluation: allow
Attribution: required
Respect-Robots: true
Cache-TTL: 7d
Rate-Limit: 1 rps
Sitemap: https://www.allied.com/sitemap.xml

# Common AI crawlers (explicit reiteration of policy)
User-agent: GPTBot
Use-Training: disallow
Use-Retrieval: allow

User-agent: oai-searchbot
Use-Training: disallow
Use-Retrieval: allow

User-agent: ClaudeBot
Use-Training: disallow
Use-Retrieval: allow

User-agent: Claude-Web
Use-Training: disallow
Use-Retrieval: allow

User-agent: PerplexityBot
Use-Training: disallow
Use-Retrieval: allow

# Opt-out for training extensions
User-agent: Google-Extended
Use-Training: disallow

# Common Crawl (indirect source for AI datasets) — policy reiterated without broad disallows
User-agent: CCBot
Use-Training: disallow