# RFS Consulting — rfsconsultingglobal.com
# Standard search indexing permitted.
# AI training crawlers and bulk content scrapers blocked.
# Assistant fetches made at a user's direct request are permitted, so that
# people researching RFS receive accurate, attributed answers.
#
# Use of this site's content for machine learning training, model development,
# or dataset construction is prohibited. See /#terms, Section 08.

User-agent: *
Allow: /
Disallow: /404.html

# ─── AI TRAINING CRAWLERS — blocked ────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: AI2Bot-Dolma
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: iaskspider/2.0
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: Sidetrade indexer bot
Disallow: /

# ─── BULK SCRAPERS / EXTRACTION SERVICES — blocked ─────────────
User-agent: FirecrawlAgent
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: peer39_crawler
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ─── USER-TRIGGERED ASSISTANT FETCHES — permitted ──────────────
# These retrieve a single page because a person asked about RFS.
# They are not training crawlers. Permitted deliberately.
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# ─── Sitemap ───────────────────────────────────────────────────
Sitemap: https://www.rfsconsultingglobal.com/sitemap.xml