# WWFM Robots.txt
# Three-tier access: Search engines (full), AI search bots (full), AI training bots (blocked)
# Last Updated: October 2026
#
# For AI agents and developers: how to read this site's data
#   Instructions for agents:  https://whatworkedforme.io/llms.txt
#   API documentation:        https://whatworkedforme.io/api/v1/docs
#   OpenAPI specification:    https://whatworkedforme.io/openapi.yaml
#
# /data-export.csv is not for automated use. Fetching it is recorded.
# Text and data mining rights are reserved: /.well-known/tdmrep.json

# ===========================================
# ALLOW LEGITIMATE SEARCH ENGINES (Full Access)
# ===========================================

User-agent: Googlebot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Bingbot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: DuckDuckBot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Slurp
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Baiduspider
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: YandexBot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Applebot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: LinkedInBot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Twitterbot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

# ===========================================
# AI SEARCH BOTS (Full Access)
# ===========================================
# These bots power AI search products (ChatGPT search, Perplexity answers,
# Claude search) and drive citation traffic. Full access since 2026-08-28 —
# the previous path-limited stanzas blocked the sitemap and homepage, which
# starved the independent AI indexes of discovery. Training bots stay blocked
# below. (Claude-Web is a retired token; Anthropic's current crawlers are
# Claude-SearchBot and Claude-User.)

User-agent: OAI-SearchBot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: ChatGPT-User
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: PerplexityBot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Perplexity-User
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Claude-SearchBot
Allow: /
Disallow: /go/
Disallow: /data-export.csv

User-agent: Claude-User
Allow: /
Disallow: /go/
Disallow: /data-export.csv

# ===========================================
# BLOCK AI TRAINING CRAWLERS (No Access)
# ===========================================
# These bots scrape content to train AI models. The same list, in the same
# order, is AI_TRAINING_BOTS in lib/rate-limit/bot-whitelist.ts, which
# answers them with a 403; a unit test keeps the two identical. Reviewed
# 2026-10-29 against github.com/ai-robots-txt/ai.robots.txt.

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: bedrockbot
Disallow: /

User-agent: cohere-ai
Disallow: /

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

User-agent: Kangaroo Bot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: aiHitBot
Disallow: /

User-agent: ApifyBot
Disallow: /

User-agent: ApifyWebsiteContentCrawler
Disallow: /

User-agent: Brightbot
Disallow: /

User-agent: ChatGLM-Spider
Disallow: /

User-agent: Crawl4AI
Disallow: /

User-agent: DeepSeekBot
Disallow: /

User-agent: DoubaoBot
Disallow: /

User-agent: ERNIEBot
Disallow: /

User-agent: FirecrawlAgent
Disallow: /

User-agent: GrokBot
Disallow: /

User-agent: xAI-Grok
Disallow: /

User-agent: iaskspider
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: LAIONDownloader
Disallow: /

User-agent: laion-huggingface-processor
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: MoonshotBot
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Panscient
Disallow: /

User-agent: QwenBot
Disallow: /

User-agent: TongyiBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: YandexAdditional
Disallow: /

User-agent: YiBot
Disallow: /

User-agent: YiyanBot
Disallow: /

User-agent: ZanistaBot
Disallow: /

# ===========================================
# DEFAULT RULE
# ===========================================
User-agent: *
Crawl-delay: 5
Allow: /
Disallow: /go/
Disallow: /data-export.csv

# Sitemaps
Sitemap: https://whatworkedforme.io/sitemap.xml