# Majeed Photography — crawl policy
# Site may be indexed for search and answer retrieval.
# AI *training / model learning* crawlers are disallowed.

User-agent: *
Allow: /
Disallow: /thank-you
Disallow: /thank-you.html
Disallow: /404.html
Disallow: /csp-report
Disallow: /asset-manifest.json

# --- AI training / dataset crawlers (disallow) ---
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: FrontPage
Disallow: /

# Answer / retrieval agents that honor robots may still use llms.txt;
# training bots above remain disallowed.

Sitemap: https://mp.notanotheraidemo.com/sitemap.xml
Host: https://mp.notanotheraidemo.com