# Salespeak — open to search and AI answer engines.
# Buyers and their AI agents both read this site; we explicitly welcome AI crawlers.

User-agent: *
Allow: /

# Search engines
# /profiles/ was Disallowed for Googlebot on 2026-08-04 to stop crawl waste
# (~40K profile URLs crawled, almost none indexed). Reversed 2026-08-29: the
# block was suppressing our largest Google surface. /profiles/ earned 89,402
# impressions and 130 clicks in the 90 days to 2026-08-26 (/profiles/lumalabs/
# alone: 26,015), and the daily impression rate fell roughly 80% after the
# block landed. The pages already serve `robots: index, follow` and self-
# canonicals, and /profiles/ is submitted in our sitemap, so the Disallow also
# contradicted every other signal we send.
#
# On the crawl waste: only 74 profile pages exist (hand-written HTML in
# salespeak-gtm/content/profiles/, served via Amplify + Cloudflare — NOT
# generated by this repo). ~40K crawled URLs against 74 real pages is ~540
# variants each, so that was almost certainly URL duplication, not 40K thin
# pages. Prune at the page level in salespeak-gtm if it recurs; robots.txt is
# the wrong instrument either way.
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# AI answer engines / training + retrieval crawlers
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

# AI-readable site summary (https://llmstxt.org)
# See: https://salespeak.ai/llms.txt

Sitemap: https://salespeak.ai/sitemap-index.xml
Sitemap: https://salespeak.ai/glossary/sitemap.xml
Sitemap: https://salespeak.ai/profiles/sitemap.xml