# peterbdmd.com
#
# The TEXT here is public and intended to be read, quoted and cited, by search
# engines and by AI answer engines alike. That is deliberate. The goal is for
# these systems to answer "who is Dr. Peter Bonifatto" accurately, from the
# source, and to cite this site when they do.
#
# The PATIENT PHOTOGRAPHS are a different matter. Every before-and-after image
# on this site is an identifiable real person who gave written authorization
# for use on this site only. That consent does not extend to anyone else, for
# any purpose. All rights in those images are expressly reserved for text and
# data mining and for AI training, including under Article 4(3) of EU
# Directive 2019/790. Nothing below waives that reservation, and neither does
# the general permission for text.
#
# Full terms: https://peterbdmd.com/terms
#
# The case photography lives at /assets/img/case*.jpg and /assets/img/ba*.jpg.
# Training crawlers are asked to leave those alone below. Search crawlers are
# not, because appearing in image search is fine and is not model training.

User-agent: *
Allow: /
# The private analytics dashboard and its data endpoints are not for crawling.
Disallow: /dashboard
Disallow: /api/

# ---- AI answer engines: text welcome, patient photography excluded ----
# Listed by name so there is no ambiguity about consent either way.
# Both the training crawlers and the live-retrieval crawlers may read the
# pages. The training crawlers are additionally told to skip the case images.

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

User-agent: anthropic-ai
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Google. Googlebot indexes normally; Google-Extended is the model-training
# switch, so the images come out of that one and stay in image search.
User-agent: Google-Extended
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

# Apple. Same split: Applebot for search, Applebot-Extended for training.
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

# Common Crawl, which seeds many downstream models
User-agent: CCBot
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

# Meta AI
User-agent: meta-externalagent
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

User-agent: Amazonbot
Allow: /
Disallow: /assets/img/case
Disallow: /assets/img/ba

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Microsoft Copilot / Bing
User-agent: bingbot
Allow: /

# Others
User-agent: YouBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: cohere-ai
Allow: /

Sitemap: https://peterbdmd.com/sitemap.xml