# robots.txt for irisagent.com
# GEO-forward configuration: explicitly allows search + AI crawlers,
# with Content-Signal directives declaring intended use of content
# (search indexing, AI input/retrieval, AI training).
# Content-Signal reference: https://content-signals.org
#
# NOTE: Semrush Site Audit reports "Invalid robots.txt format" for this file.
# That is a false positive: Content-Signal is not yet in its known-directive
# list. Per RFC 9309 conformant parsers ignore unrecognized lines, so Google,
# Bing and the AI crawlers below are unaffected. Keep these directives.

# Default: allow all user agents
User-Agent: *
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Search engine crawlers
User-Agent: Bingbot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: Amazonbot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: DuckAssistBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# OpenAI
User-Agent: GPTBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: OAI-SearchBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: ChatGPT-User
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Anthropic
User-Agent: ClaudeBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: Claude-User
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: Claude-SearchBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Perplexity
User-Agent: PerplexityBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: Perplexity-User
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Google (AI and extended)
User-Agent: Google-Extended
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: GoogleOther
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Apple Intelligence
User-Agent: Applebot-Extended
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Meta AI
User-Agent: Meta-ExternalAgent
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-Agent: Meta-ExternalFetcher
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# ByteDance
User-Agent: Bytespider
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Common Crawl (used by many LLM training pipelines)
User-Agent: CCBot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Cohere
User-Agent: cohere-ai
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Diffbot (knowledge graph used by several AI vendors)
User-Agent: Diffbot
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

Sitemap: https://irisagent.com/sitemap-index.xml
Sitemap: https://irisagent.com/sitemap-0.xml