# hire-web-designer.com

# ─────────────────────────────────────────────────────────────
# SEARCH ENGINES
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /

# Never block these. Blocking /favicon/ stops your icon appearing
# in search results; blocking /social/ breaks every link preview.
Allow: /favicon/
Allow: /social/

Disallow: /*?s=
Disallow: /*?replytocom=
Disallow: /thank-you/

# Google needs image access or the favicon will not render in results
User-agent: Googlebot-Image
Allow: /

# ─────────────────────────────────────────────────────────────
# AI CRAWLERS
#
# Training crawlers and search crawlers are now SEPARATE agents.
# That distinction is the whole decision:
#
#   Training crawler  -> your content becomes model weights.
#                        You are never credited. Blocking costs
#                        you nothing in visibility.
#   Search crawler    -> your content becomes a CITED answer that
#                        can send a visitor back to you. Blocking
#                        removes you from AI answers entirely.
#
# The common mistake is blocking GPTBot and OAI-SearchBot together
# in one "no AI" reflex. That blocks training AND deletes you from
# ChatGPT search results.
#
# POLICY BELOW: allow everything.
# For a new service business, being findable beats being protected —
# your pages are marketing, not proprietary IP. If you later decide
# you don't want to feed model training, uncomment the block at the
# bottom of this file. Citation eligibility is unaffected either way.
# ─────────────────────────────────────────────────────────────

# --- Search and answer agents: these make you citable ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Applebot
Allow: /

# --- Training agents ---
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

# ─────────────────────────────────────────────────────────────
# OPT OUT OF TRAINING, KEEP CITATIONS
# Uncomment this block to stop your content feeding model training
# while staying fully eligible for AI-search citations. Delete the
# matching Allow rules above if you do.
# ─────────────────────────────────────────────────────────────
# User-agent: GPTBot
# Disallow: /
# User-agent: ClaudeBot
# Disallow: /
# User-agent: Google-Extended
# Disallow: /
# User-agent: Applebot-Extended
# Disallow: /
# User-agent: CCBot
# Disallow: /
# User-agent: Bytespider
# Disallow: /

Sitemap: https://hire-web-designer.com/sitemap.xml