# trysumora.com/robots.txt
#
# Policy:
#  * Answer-engine / search crawlers that surface content to users are
#    explicitly ALLOWED below (GPTBot feeds ChatGPT answers, ClaudeBot feeds
#    Claude, PerplexityBot feeds Perplexity, Google-Extended powers Gemini
#    grounding, etc).
#  * Training-only crawlers (CCBot, Bytespider) are DISALLOWED: we want our
#    pages IN the answer engines, not wholesale in training corpora.
#  * Content-Signal expresses the same split in machine-readable form:
#    searchable and AI-answerable, but not ai-train.
#
# Human docs: https://trysumora.com/about · Agent index: https://trysumora.com/llms.txt

User-agent: *
Allow: /

# --- Allowed: answer-engine & assistant crawlers ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: DuckAssistBot
Allow: /

# --- Blocked: bulk-training-only crawlers ---
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

# Sitemaps and structured-data feeds.
Sitemap: https://trysumora.com/sitemap.xml

# NLWeb Schema Map: structured-data feeds for natural-language web agents.
schemamap: https://trysumora.com/.well-known/schemamap.xml

# Content signals: allow search indexing and AI answer use, opt out of model training.
Content-Signal: search=yes, ai-train=no, train=no