# Allow all legitimate crawlers (search engines, social previews)
User-agent: *
Allow: /

Sitemap: https://spec24.dev/sitemap.xml

# ─────────────────────────────────────────────────────────────
# Allow AI ANSWER / SEARCH engines — we WANT to be cited by these.
# These bots power live citations in ChatGPT search, Perplexity and
# Claude answers (they are NOT model-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: /

# ─────────────────────────────────────────────────────────────
# Block AI MODEL-TRAINING crawlers — they scrape for training and
# do not send traffic or citations back.
# ─────────────────────────────────────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

# ── Legacy / misc training + scraper bots ──
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: FriendlyCrawler
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: GoogleOther-Image
Disallow: /

User-agent: GoogleOther-Video
Disallow: /

User-agent: iaskspider/2.0
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: ISSCyberRiskCrawler
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Sidetrade indexer bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VeaceBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: YouBot
Disallow: /