User-agent: *
Allow: /

Disallow: /node_modules/
Disallow: /*.bak$
Disallow: /submit.php
Disallow: /LaundryDaddy/
# Server-side PHP partials (header/footer/head). Pulled in by pages, never URLs.
# .htaccess also 403s them; this stops crawlers asking.
Disallow: /includes/
# Per-customer Daddy POS short URLs — redirected to pos.laundrydaddy.com.
# Must never appear in search results.
Disallow: /i/
Disallow: /t/

# =============================================================
# AI POLICY
#
# Laundry Daddy wants to be discovered via AI-powered search
# (Google AI Overviews, ChatGPT, Perplexity, Copilot, Claude answers)
# because these crawlers cite the source, which drives traffic.
#
# But Laundry Daddy does NOT permit its content or photos to be
# used for training generative AI models, or scraped in bulk
# for commercial datasets. Those crawlers are blocked below,
# and .htaccess enforces the block at the server level for
# operators that ignore robots.txt.
# =============================================================

# === BLOCKED: AI model training crawlers ====================
# These fetch content to train LLMs with no citation back.

# OpenAI model training
User-agent: GPTBot
Disallow: /

# Anthropic model training
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Common Crawl, feeds most LLM training datasets
User-agent: CCBot
Disallow: /

# ByteDance / TikTok / Doubao training
User-agent: Bytespider
Disallow: /

# Meta AI training
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# Amazon (Alexa + AI training)
User-agent: Amazonbot
Disallow: /

# Other training / bulk-scraper bots
User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: MistralAI-User
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Scrapy
Disallow: /

# === ALLOWED: AI search and citation crawlers ===============
# These fetch to answer user queries and link back to the source.

# ChatGPT Search (SearchGPT), cites sources
User-agent: OAI-SearchBot
Allow: /

# ChatGPT user browsing, cites sources when users click
User-agent: ChatGPT-User
Allow: /

# Claude user-initiated browsing, cites sources
User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity, cites sources
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# DuckDuckGo AI answers, cites sources
User-agent: DuckAssistBot
Allow: /

# Meta link unfurling (when users share URLs)
User-agent: Meta-ExternalFetcher
Allow: /

# Google Gemini, explicitly allowed for AI Overviews presence
User-agent: Google-Extended
Allow: /

# Apple Intelligence, explicitly allowed for AI answer presence
User-agent: Applebot-Extended
Allow: /

# (Googlebot, Bingbot, Applebot, etc. inherit Allow from User-agent: *)

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