# TechJapan LLC — https://www.tech-japan.jp
#
# Everything here is public and meant to be read, by people and by machines.
# There is no crawl budget to protect: the site is a few dozen static pages
# with no images to fetch.

User-agent: *
Allow: /

# --- Search engines -------------------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# --- Answer engines and model crawlers ------------------------------------
#
# GPTBot trains; OAI-SearchBot fetches for ChatGPT Search; ChatGPT-User
# fetches a page a person asked about. They are three different agents, and
# allowing only one of them means the other two never quote you.

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
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: YouBot
Allow: /

# --- Machine-readable surface ---------------------------------------------
#
# These three are generated from one source file together with the pages
# themselves, so a page and its machine-readable form cannot disagree.
# Every claim carries a status; "designed" is not "built", and "built" is
# not "available".
#
#   https://www.tech-japan.jp/llms.txt        index, one file
#   https://www.tech-japan.jp/llms-full.txt   every published fact, one fetch
#   https://www.tech-japan.jp/facts.json      the same facts as JSON

Sitemap: https://www.tech-japan.jp/sitemap.xml