# Sprkly robots.txt
#
# ⚠️ IMPORTANT: Cloudflare's "AI Audit / Block AI bots" managed feature can inject
# an additional managed block ABOVE this file at the edge that DISALLOWS AI
# crawlers (GPTBot, ClaudeBot, Google-Extended, CCBot, Bytespider, etc.). To be
# included in AI search answers, that managed feature must be turned OFF in the
# Cloudflare dashboard (Scrape Shield / AI Audit / Manage robots.txt). This file
# alone cannot override the edge-injected block.

# Default: allow normal search crawlers (Googlebot, Bingbot, etc.)
User-agent: *
Disallow: /api/
Allow: /api/media/ig

# ── AI search / answer engines — explicitly welcomed so we surface in AI answers ──
User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: GPTBot
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: Claude-User
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

User-agent: cohere-ai
Allow: /
Disallow: /api/

# ── Instagram / Facebook media crawlers ──
# Required for Instagram Graph API carousel & reel publishing (code 9004 fix)
User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

# AI grounding files (Answer Engine Optimization)
# Curated index: https://sprkly.app/llms.txt
# Full article text: https://sprkly.app/llms-full.txt

Sitemap: https://sprkly.app/sitemap.xml