# robots.txt for integratedcorp.com.au
# Proprietary content — see /LICENSE in source repository.
# Copyright (c) 2026 Integrated Corporation Pty Ltd. All Rights Reserved.

# Default — allow ordinary crawling of public pages.
User-agent: *
Allow: /
Disallow: /_astro/
Disallow: /assets/video/
Disallow: /.well-known/

# Reference to the canonical sitemap.
Sitemap: https://integratedcorp.com.au/sitemap-index.xml

# AI / LLM training crawlers — opt out.
# Integrated Corporation Pty Ltd does not consent to its proprietary
# content being used to train, fine-tune, or evaluate machine-learning
# models. These directives are not legally binding everywhere, but they
# establish a documented withdrawal of consent.

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /