# robots.txt for greenarrow.app
# Green Arrow Consultancy Ltd, Cardiff, Wales, United Kingdom
# Last updated 2026-09-04
#
# We want to be read, indexed, retrieved and cited. Every documented search
# crawler and AI crawler is allowed the whole site. If you operate a crawler
# that is being blocked in error, contact info@greenarrowconsultancy.com.

# ── Content Signals ──────────────────────────────────────────────────
# search:   this content may be used to build a search index.
# ai-input: this content may be retrieved and used to generate an answer.
# ai-train: this content may be used to train or fine-tune a model.
# We say yes to all three. Attribution with a link is expected.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /poc/
Disallow: /poc-admin/
Disallow: /request/
Disallow: /hr-admin/
Disallow: /hr-employees/
Disallow: /analytics-ai-report/
Disallow: /ENR-Site-monitoring/
Disallow: /*?snap

# ── Search engines ──────────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: Discordbot
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: WhatsApp
Allow: /

# ── AI crawlers, assistants and answer engines ──────────────────────
# Training crawlers, retrieval crawlers and user-triggered fetchers are all
# welcome. Blocking a retrieval or user agent removes a site from AI answers
# entirely, which is not what we want.

User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

User-agent: FacebookBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Cohere-AI
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Diffbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: omgili
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: omgilibot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: YouBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: PetalBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Timpibot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Ai2Bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Ai2Bot-Dolma
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ImagesiftBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Kangaroo Bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: MistralAI-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

User-agent: Firecrawl
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: SemrushBot-OCOB
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Scrapy
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# ── Discovery ───────────────────────────────────────────────────────
Sitemap: https://greenarrow.app/sitemap.xml
LLMS: https://greenarrow.app/llms.txt
# Full text corpus: https://greenarrow.app/llms-full.txt
# Every page is also served as markdown at <page>index.md
# RSS: https://greenarrow.app/feed.xml