# https://www.robotstxt.org/robotstxt.html
#
# LAUNCHED 2026-09-25. Search indexing and AI/answer-engine crawling are both
# open. The pre-launch noindex header was removed from vercel.json the same day;
# see docs/prelaunch-noindex.md for how that gate worked and why crawling was
# never blocked while it was on.

# Allow all standard search engine bots
User-agent: *
Allow: /
Disallow:

# /app-shell.html is the empty client-side fallback document that URLs without
# static HTML of their own are served from. It is a delivery mechanism, not a
# page, and has no content to index.
Disallow: /app-shell.html

# AI / answer-engine crawlers: OPEN. The site publishes a plain-language summary
# for them at /llms.txt and /ai, and the FAQ answers on every page are written
# to be quoted. Reopened at launch, 2026-09-25.

# OpenAI / ChatGPT (Training and Search)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Google AI (Gemini / AI Overviews)
User-agent: Google-Extended
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Common Crawl (Open-source data used by many AI models)
User-agent: CCBot
Allow: /

# Apple AI
User-agent: Applebot-Extended
Allow: /

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

# Plain-text summary of the company for automated readers, and its
# human-readable equivalent. Both are crawlable under the rules above.
# https://www.getsimpliroofs.com/llms.txt
# https://www.getsimpliroofs.com/ai