# robots.txt — rieder.cc
# Framer serves this from Site Settings → SEO → robots.txt.

# ── Default: everything crawlable ────────────────────────────────
User-agent: *
Allow: /

# Old Sanity-era API endpoints (no longer pages)
Disallow: /api/

# Query-string variants of filtered listing pages (sample-order,
# products, projects) — the canonical unfiltered pages remain
# crawlable, this only prunes the filter-permutation duplicates.
# Prefix wildcards cover the numbered variants (textures-2,
# textures-3, surfaces-2, …) and params in any position (?x=&y=).
Disallow: /*?*materials-
Disallow: /*?*palettes-
Disallow: /*?*textures-
Disallow: /*?*surfaces-
Disallow: /*?*colors=

# ── AI / LLM crawlers: explicitly allowed ────────────────────────
# Rieder publishes /llms.txt and wants to be accurately represented
# in AI answers. Flip these to "Disallow: /" only if the company
# decides against inclusion in AI training corpora.

# OpenAI (training / search / user-triggered fetch)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

# Google AI training (Gemini) — separate from normal Google Search
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Apple Intelligence training
User-agent: Applebot-Extended
Allow: /

# Common Crawl (feeds many open datasets)
User-agent: CCBot
Allow: /

# ── Sitemap ──────────────────────────────────────────────────────
Sitemap: https://www.rieder.cc/sitemap.xml