# llms.txt for indataipm.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: /trade-order-management/
Allow: /portfolio-accounting-software/
Allow: /portfolio-management-software/
Allow: /bi-reporting/
Allow: /indata-ipm-portfolio-architect-ai/
Allow: /ipm-portal/
Allow: /architect-ai-reporting/
Allow: /ipm-cloud/
Allow: /institutional-investment-management-software/
Allow: /wealth-managers-and-advisors/
Allow: /hedge-fund-management-software/
Allow: /pension-sovereign-wealth-fund-management/
Allow: /portfolio-accounting-operations-management/
Allow: /portfolio-management-and-trading/
Allow: /compliance-as-a-service/
Allow: /it-system-administrators-software/
Allow: /back-office-managed-services/
Allow: /about/
Allow: /blog-articles/
# 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.indataipm.com/sitemap_index.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