# Robots.txt for Schedchie
# 
# Note: Disallow does NOT prevent indexing if pages are linked.
# For true noindex, pages use X-Robots-Tag or meta robots.
# Disallow here is primarily to reduce crawl load.

User-agent: *

# Reduce crawl load on private/auth areas
# (These also have noindex via headers for true indexing prevention)
Disallow: /dashboard
Disallow: /admin
Disallow: /api
Disallow: /settings
Disallow: /oauth-callback

# Auth flows - low value, reduce crawl
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /choose-plan

# Everything else is allowed
Allow: /

# Content Signals (contentsignals.org / IETF draft):
# we WANT search indexing, AI answers, and AI training:
# AI citations are this site's primary acquisition channel.
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# ============================================
# AI Crawler Access
# OpenAI crawlers for AI training and search features.
# GPTBot: Used for training AI models
# OAI-SearchBot: Used for ChatGPT search features (citations)
# Allowing both for potential AI visibility/citations.
# ============================================
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ============================================
# Other AI crawlers (for visibility)
# Claude-Web / Anthropic-AI are legacy names kept for
# old crawlers; ClaudeBot / Claude-User / Claude-SearchBot
# are Anthropic's current fleet.
# ============================================
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: PerplexityBot
Allow: /

Sitemap: https://www.schedchie.com/sitemap.xml