# Ecosulis robots.txt
# Updated 2026-07-16
#
# Stance: Ecosulis welcomes AI answer engines (real-time search and citation)
# but does NOT permit its content to be used to train or fine-tune AI models.
#
# Content signals (machine-readable usage permissions):
#   search    = building a search index and returning links / short excerpts
#   ai-input  = feeding content into AI models in real time (RAG, grounding,
#               generative search answers)
#   ai-train  = training or fine-tuning AI models
#
# A "no" signal is an express reservation of rights under Article 4 of EU
# Directive 2019/790 on copyright in the Digital Single Market.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# ─── AI answer / search engines — ALLOWED ───────────────────────────────
# These crawl to surface and cite Ecosulis in real-time AI answers and
# search results. They are not training crawlers.

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ─── AI training crawlers — BLOCKED ─────────────────────────────────────
# These collect content to train or fine-tune models, or to control whether
# content is used for AI training/grounding. Disallowed per the no-train stance.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Amazonbot
Disallow: /

Sitemap: https://ecosulis.co.uk/sitemap.xml