User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# ── AI training crawlers (model training corpora) ──────────────
# Allowing these lets future model versions include BossWorks content.
# Disallow any of these if you don't want your content in training data.

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Amazonbot
Allow: /



# ── AI answer crawlers (live citation when an LLM answers) ─────
# These fetch your page in real time during a user's query. This is
# what gets your content cited in ChatGPT/Perplexity/Claude answers.

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /



# ── Default ─────────────────────────────────────────────────────
# Anything not named above gets the same access. Tighten this if you
# want a strict allow-list rather than allow-by-default.

User-agent: *
Allow: /
Disallow: /*?utm_
Disallow: /*&utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*?mc_cid=
Disallow: /_next/static/
Disallow: /_next/image

# ── Environment files ───────────────────────────────────────────
Disallow: /.env
Disallow: /.env.*
Disallow: /.env*
Disallow: /aws.env
Disallow: /secrets.env
Disallow: /us/.env
Disallow: /us/.env.*
Disallow: /us/.env*
Disallow: /us/sendgrid.env
Disallow: /us/stripe.env
Disallow: /us/stripe/.env
Disallow: /us/dev/.env
Disallow: /us/staging/.env
Disallow: /us/laravel/.env
Disallow: /us/backend/.env
Disallow: /us/admin/.env
Disallow: /us/api/.env
Disallow: /us/var/www/.env
Disallow: /us/%2F.env
Disallow: /us/config.env
Disallow: /blog/.env
Disallow: /blog/.env.*
Disallow: /blog/app/.env
Disallow: /frontend/.env
Disallow: /server/.env
Disallow: /server/.env.production
Disallow: /src/.env
Disallow: /html/.env
Disallow: /web/.env
Disallow: /www/.env
Disallow: /core/.env
Disallow: /admin/.env
Disallow: /client/.env
Disallow: /app/.env
Disallow: /app/.env.prod
Disallow: /config/.env
Disallow: /deploy/.env
Disallow: /dist/.env
Disallow: /backend/.env
Disallow: /laravel/.env
Disallow: /project/.env
Disallow: /repo/.env

# ── Git directories & files ─────────────────────────────────────
Disallow: /.git/
Disallow: /us/.git/
Disallow: /blog/.git/
Disallow: /assets/.git/
Disallow: /frontend/.git/
Disallow: /site/.git/
Disallow: /web/.git/
Disallow: /project/.git/
Disallow: /admin/.git/
Disallow: /htdocs/.git/
Disallow: /html/.git/
Disallow: /build/.git/
Disallow: /laravel/.git/
Disallow: /symfony/.git/
Disallow: /v1/.git/

# ── WordPress admin & sensitive files ───────────────────────────
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-config.php
Disallow: /xmlrpc.php
Disallow: /us/xmlrpc.php
Disallow: /blog/xmlrpc.php
Disallow: /blog/wp-admin/

# ── Credential & config files ───────────────────────────────────
Disallow: /google-credentials.json
Disallow: /gcp-credentials.json
Disallow: /credentials.json
Disallow: /secrets.json
Disallow: /service-account.json
Disallow: /config.json
Disallow: /config.js
Disallow: /web.config
Disallow: /private/
Disallow: /us/credentials.json
Disallow: /us/secrets.json
Disallow: /us/settings.py
Disallow: /us/web.config
Disallow: /deploy/credentials.json

# ── PHP debug/info files ─────────────────────────────────────────
Disallow: /us/info.php
Disallow: /us/test.php
Disallow: /blog/info.php
Disallow: /blog/phpinfo.php

Sitemap: https://bossworks.ai/sitemap.xml