# Robots.txt for Pixelmojo
# Production: https://www.pixelmojo.io
# AI-native product studio optimized for modern search & AI discovery

# === Global Defaults (All Crawlers) ===
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /_next/data/
Allow: /_next/static/
Disallow: /private/
Disallow: /*.json$
Disallow: /blogs/design/
Disallow: /search
Crawl-delay: 1

# === AI Browsing + Curated Training Bots (Allowed) ===
# Browsing bots fetch content for AI-assisted answers and search.
# Training bots in this section feed AI engines we want citing Pixelmojo.
# Policy evolved 2026-05-16 — see /blogs/optimized-ai-search-pixelmojo-results

User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: GoogleOther
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: TavilyBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: anthropic-ai
User-agent: Applebot-Extended
Allow: /
Allow: /blogs/
Allow: /services/
Allow: /projects/
Allow: /about/
Allow: /pricing/
Allow: /vector
Allow: /hive
Allow: /capabilities
Allow: /tools/
Allow: /platform
Allow: /labs/
Allow: /topics/
Allow: /vs/
Allow: /best-ai-visibility-agencies
Allow: /author/
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai-capabilities-factsheet.txt
Allow: /api/ask
Allow: /.well-known/ai-plugin.json
Allow: /.well-known/openapi.json
Disallow: /api/
Disallow: /admin/
Disallow: /_next/data/
Allow: /_next/static/
Disallow: /private/
Crawl-delay: 1

# === Data Brokers + Adversarial Scrapers (Blocked) ===
# These bots either resell scraped data (Diffbot, Omgili) or train models
# we have no strategic alignment with. Blocked for IP-resale concerns.

User-agent: cohere-ai
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: Diffbot
User-agent: Omgili
User-agent: Omgilibot
User-agent: img2dataset
Allow: /llms.txt
Allow: /ai-capabilities-factsheet.txt
Disallow: /

# === Sitemap ===
Sitemap: https://www.pixelmojo.io/sitemap.xml