# https://www.wilhelmina.com
#
# Policy: AI TRAINING crawlers are refused. AI SEARCH and ANSWER engines are
# welcome, because they send clients to Wilhelmina. The two are different bots
# run by the same companies, and refusing both would hide this agency's talent
# from every buyer who now starts a search in ChatGPT, Claude, Perplexity or Siri.
#
# robots.txt only binds crawlers that choose to obey it. Bytespider in
# particular ignores it, which is why the server-side guard refuses the same
# list again, and why /.well-known/tdmrep.json reserves the text and data mining
# rights independently of any user-agent. All three read one list. Keep them in step.

# Content Signals Policy (contentsignals.org). States what the content may be
# USED for, which Disallow cannot say: indexing yes, live AI answers yes,
# model training no. Repeated on the search group below, because a named
# crawler never reads this record.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /api

# ---------------------------------------------------------------- AI training
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: TikTokSpider
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: omgili
User-agent: omgilibot
User-agent: Timpibot
User-agent: PanguBot
User-agent: DeepSeekBot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Webzio-Extended
Disallow: /

# ------------------------------------------- Search and answer engines: allowed
# Named so nobody moves one into the block list by accident: OAI-SearchBot is
# not GPTBot, Claude-SearchBot is not ClaudeBot, Applebot is not
# Applebot-Extended.
#
# The Disallow set is repeated here deliberately. A crawler obeys only its
# single most-specific matching group, so the moment Googlebot is named it
# stops reading "User-agent: *" — a group of "Allow: /" alone would hand it
# /api, which the site has kept out of robots since before this file.
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /api

Sitemap: https://www.wilhelmina.com/sitemap.xml