# robots.txt for commuteimpact.com
# Policy (founder decision 2026-09-26): search engines, AI search crawlers and
# AI assistants fetching a page for a user are allowed. Crawlers that collect
# content to train AI models are not.
#
# Allowed bots are deliberately NOT named. Under RFC 9309 a bot with its own
# group ignores the "*" group, so naming it would drop the Disallow rules below.
# There are no Allow lines on purpose: an Allow that ties with a Disallow wins,
# so an Allow can silently undo a block.
#
# /api/ is deliberately NOT disallowed. Search engines fetch it while rendering
# pages; a blocked fetch makes a published report render as "not found" with a
# noindex tag. robots.txt is not access control.

User-agent: *
Disallow: /admin/
Disallow: /press-kit-*

# AI model training crawlers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: MistralAI-Training
User-agent: CCBot
User-agent: Bytespider
User-agent: AI2Bot
User-agent: AI2Bot-Dolma
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: Webzio-Extended
User-agent: omgili
User-agent: omgilibot
Disallow: /

# SEO scrapers
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: MJ12bot
Disallow: /

Sitemap: https://commuteimpact.com/sitemap.xml