# robots-ai.txt for Photo Planète Charmilles (https://www.photoplanete.ch)
# Specification: https://www.ai-visibility.org.uk/specifications/robots-ai-txt/
# Supplements robots.txt — does not replace it
# Last updated: 2026-10-31
#
# Policy (matches robots.txt, ai.txt and ai.json): a local shop that wants to be found. Content may be
# indexed for search, used as AI input (retrieval, grounding, citations) and used to train or fine-tune
# AI models. Only bulk data collectors with no visibility in return are blocked. Each group is
# self-contained: a crawler obeys only its most specific matching group.

# ============================================================
# AI SEARCH & RETRIEVAL CRAWLERS — ALLOW
# ============================================================

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 2

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 2

User-agent: ChatGPT Agent
Allow: /
Crawl-delay: 2

User-agent: Operator
Allow: /
Crawl-delay: 2

User-agent: Claude-SearchBot
Allow: /
Crawl-delay: 2

User-agent: Claude-User
Allow: /
Crawl-delay: 2

User-agent: Claude-Web
Allow: /
Crawl-delay: 2

User-agent: PerplexityBot
Allow: /
Crawl-delay: 2

User-agent: Perplexity-User
Allow: /
Crawl-delay: 2

User-agent: MistralAI-User
Allow: /
Crawl-delay: 2

User-agent: MistralAI-Index
Allow: /
Crawl-delay: 2

User-agent: Gemini-Deep-Research
Allow: /
Crawl-delay: 2

User-agent: Google-NotebookLM
Allow: /
Crawl-delay: 2

User-agent: GoogleAgent-Mariner
Allow: /
Crawl-delay: 2

User-agent: Meta-ExternalFetcher
Allow: /
Crawl-delay: 2

User-agent: meta-webindexer
Allow: /
Crawl-delay: 2

User-agent: Applebot
Allow: /
Crawl-delay: 2

User-agent: DuckAssistBot
Allow: /
Crawl-delay: 2

User-agent: Bravebot
Allow: /
Crawl-delay: 2

User-agent: YouBot
Allow: /
Crawl-delay: 2

User-agent: AzureAI-SearchBot
Allow: /
Crawl-delay: 2

User-agent: PhindBot
Allow: /
Crawl-delay: 2

User-agent: TavilyBot
Allow: /
Crawl-delay: 2

User-agent: DeepSeekBot
Allow: /
Crawl-delay: 2

User-agent: Amzn-SearchBot
Allow: /
Crawl-delay: 2

User-agent: cohere-ai
Allow: /
Crawl-delay: 2

User-agent: iaskspider
Allow: /
Crawl-delay: 2

User-agent: Google-Firebase
Allow: /
Crawl-delay: 2

# ============================================================
# AI TRAINING CRAWLERS — ALLOW
# A photo shop in Geneva gains from being known by the models themselves.
# ============================================================

User-agent: GPTBot
Allow: /
Crawl-delay: 2

User-agent: ClaudeBot
Allow: /
Crawl-delay: 2

User-agent: anthropic-ai
Allow: /
Crawl-delay: 2

User-agent: Google-Extended
Allow: /
Crawl-delay: 2

User-agent: Applebot-Extended
Allow: /
Crawl-delay: 2

User-agent: Meta-ExternalAgent
Allow: /
Crawl-delay: 2

User-agent: meta-externalagent
Allow: /
Crawl-delay: 2

User-agent: FacebookBot
Allow: /
Crawl-delay: 2

User-agent: Amazonbot
Allow: /
Crawl-delay: 2

User-agent: MistralAI-Training
Allow: /
Crawl-delay: 2

User-agent: CCBot
Allow: /
Crawl-delay: 2

User-agent: AI2Bot
Allow: /
Crawl-delay: 2

User-agent: Ai2Bot-Dolma
Allow: /
Crawl-delay: 2

User-agent: cohere-training-data-crawler
Allow: /
Crawl-delay: 2

User-agent: Diffbot
Allow: /
Crawl-delay: 2

# ============================================================
# BULK DATA COLLECTORS — BLOCK
# ============================================================

User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: LAIONDownloader
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Brightbot 1.0
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: webzio-extended
Disallow: /

# ============================================================
# DEFAULT FOR UNLISTED AI CRAWLERS
# ============================================================

User-agent: *
Allow: /
Disallow: /404.html
Disallow: /500.html

# ============================================================
# SITEMAPS
# ============================================================

Sitemap: https://www.photoplanete.ch/sitemap.xml

# ============================================================
# AI DISCOVERY FILES PUBLISHED ON THIS HOST
# (Discovery: directive per robots-ai.txt spec §Directives; every URL returns 200)
# ============================================================

Discovery: https://www.photoplanete.ch/llms.txt
Discovery: https://www.photoplanete.ch/llms-full.txt
Discovery: https://www.photoplanete.ch/llms.html
Discovery: https://www.photoplanete.ch/ai.txt
Discovery: https://www.photoplanete.ch/ai.json
Discovery: https://www.photoplanete.ch/identity.json
Discovery: https://www.photoplanete.ch/brand.txt
Discovery: https://www.photoplanete.ch/faq-ai.txt
Discovery: https://www.photoplanete.ch/developer-ai.txt
Discovery: https://www.photoplanete.ch/okf/index.md
Discovery: https://www.photoplanete.ch/humans.txt