User-agent: *
Allow: /

# Keep the CMS admin and its API out of search indexes
Disallow: /keystatic
Disallow: /api/keystatic

# The site is static with no server-side search, so `?s=` and `/search/` resolve
# to whatever page the path happens to be (usually the homepage) rather than any
# real results. Spam sites inject backlinks pointing at these to get their text
# indexed against our domain (seen live: /?s=<spam phrase>); GSC was crawling
# them despite the self-referencing canonical already pointing at the clean URL.
# Blocking the pattern stops the crawl rather than relying on canonical alone.
Disallow: /*?s=
Disallow: /search/

# AI answer engines and their crawlers are explicitly welcome: Putti optimises
# for GEO/AEO (see /llms.txt), so we want these to index and cite the site.
# Listed by name so the intent is on the record even though `*` already allows
# them; tighten or remove a line here to opt a specific crawler out later.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
User-agent: Bytespider
Allow: /

# A machine-readable site overview for LLMs / answer engines (llmstxt.org).
# Not a standard robots directive, kept here for discoverability.
# llms.txt: https://www.puttiapps.com/llms.txt

Sitemap: https://www.puttiapps.com/sitemap-index.xml