# Team Armored Roofing — https://teamarmored.com
#
# ── IF THIS FILE STOPS MATCHING WHAT'S LIVE, READ THIS ──────────────────────────
#
# Cloudflare's "Managed robots.txt" PREPENDS its own block — wrapped in
# "BEGIN/END Cloudflare Managed content" — to whatever is served here, and no edit to
# this file can remove those lines. It was ON from ~2026-07-26 until 2026-08-10, during
# which the live file carried two `User-agent: *` groups and disallowed Amazonbot,
# Applebot-Extended, Bytespider, CCBot, ClaudeBot, CloudflareBrowserRenderingCrawler,
# Google-Extended, GPTBot and meta-externalagent regardless of the policy below.
#
# Disabled 2026-08-10; verified live byte-identical to this file. If the managed block
# ever reappears, the toggle is NOT under "AI Crawl Control" (where it sounds like it
# should be) — it is:
#   Cloudflare dashboard → teamarmored.com → Security → Settings
#     → filter "Bot traffic" → "Set your preference to block training in robots.txt"
#
# There is no public API for it; it has to be flipped in the dashboard.
# Verify with:  curl -s https://teamarmored.com/robots.txt | grep -c "BEGIN Cloudflare"
#
# ── POLICY ──────────────────────────────────────────────────────────────────────
# Training crawlers are blocked; retrieval and search crawlers are allowed.
#
# The distinction matters commercially. A training crawler ingests the site into model
# weights and sends nothing back. A retrieval crawler fetches a page to answer someone's
# live question and typically cites the source — that is referral traffic, and for a local
# service business it is the same kind of visibility as a search result. Blocking both
# (the Cloudflare default) protects the content and costs us the referrals; blocking only
# the first keeps the protection and keeps the visibility.

# ── Search engines — full access ────────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# ── AI retrieval / search — allowed, these cite and refer ───────────────────────
# Google-Extended governs Gemini app and Vertex AI grounding ONLY. Google states it is
# not a Search ranking signal, and AI Overviews are drawn from the Search index (governed
# by ordinary snippet directives), so this line does not affect AI Overviews either way.
# Allowed because Gemini grounding cites its sources — that is referral traffic.
User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ── AI training corpora — blocked, no referral value ────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Omgilibot
Disallow: /

# ── Everything else ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /

# Review detail pages are noindex and exist only as anchors for review markup.
Disallow: /reviews/*/

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