# whitewood.ai — robots.txt
#
# White Wood is a GEO studio. Being read and cited by answer engines IS the product.
# Most sites block AI crawlers; blocking the crawlers we sell visibility inside would be
# absurd. Everything below is a deliberate welcome, not an oversight.
#
# Note: the wildcard block already permits every crawler. The named blocks are a
# STATEMENT OF INTENT — a prospect who checks this file should see it said out loud.
#
# Crawler names verified against primary docs on 2026-07-12. They change; re-verify.
# A stale user-agent name is a silent no-op, which is the worst kind of bug: it looks
# like it works.

User-agent: *
Allow: /
Disallow: /ops/

# ── ANSWER / SEARCH CRAWLERS ────────────────────────────────────────────────
# These decide whether White Wood appears IN THE ANSWER. They are the product.
# Note they are SEPARATE from the training crawlers below — allowing GPTBot does
# not put you in ChatGPT's search results; OAI-SearchBot does.

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# ── USER-INITIATED FETCHES ──────────────────────────────────────────────────
# A human asked the assistant a question and it went to look. Always welcome.

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

# ── TRAINING CRAWLERS ───────────────────────────────────────────────────────
# A real choice, made on purpose: being in the weights is the deepest form of being
# the answer. A studio that sells AI visibility does not opt out of the models.

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

Sitemap: https://whitewood.ai/sitemap-index.xml
Sitemap: https://whitewood.ai/sitemap.xml