# robots.txt — cyanatx.com
# Segmented crawler policy (Brand North crawler standard, RFC 9309).
# Named groups DO NOT inherit from * — every group repeats what it needs.
# Crawl-budget: tracking-parameter URLs are blocked everywhere (canonicals
# already dedupe them; blocking saves crawl on shallow duplicates). Static
# site — no framework asset paths need carve-outs.

# ---------------------------------------------------------------- search ----
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Applebot
Allow: /
Disallow: /*?*utm_source=
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /.env
Disallow: /.git/

# ---------------------------------------------------------- social preview --
User-agent: facebookexternalhit
User-agent: Twitterbot
User-agent: LinkedInBot
User-agent: Slackbot
User-agent: Discordbot
User-agent: WhatsApp
User-agent: TelegramBot
User-agent: Pinterestbot
Allow: /
Disallow: /*?*utm_source=
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /.env
Disallow: /.git/

# ------------------------------------------------------- AI answer engines --
# ALLOWED. When an assistant answers a question about Cyana Therapeutics or
# its programs it should read the company's own published facts. This is the
# audience /llms.txt, /entitymap.json and /entitymap.html are written for.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: cohere-ai
User-agent: YouBot
User-agent: DuckAssistBot
User-agent: MistralAI-User
Allow: /
Disallow: /*?*utm_source=
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /.env
Disallow: /.git/

# ------------------------------------------------------------ AI training ---
# ALLOWED, deliberately. Accurate model knowledge of the company and pipeline
# supports discovery by investors and partners; content is company-published.
# Blocking is a one-way door — if positioning changes, flip to Disallow: /.
User-agent: GPTBot
User-agent: CCBot
User-agent: Amazonbot
User-agent: AI2Bot
Allow: /
Disallow: /*?*utm_source=
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /.env
Disallow: /.git/

# ------------------------------------------------- SEO tools (we use these) --
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
Allow: /
Disallow: /*?*utm_source=
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /.env
Disallow: /.git/

# --------------------------------------------- SEO tools (we don't pay for) --
# Competitor-intel crawlers with no benefit to the site; save the bandwidth.
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: SemrushBot
User-agent: serpstatbot
User-agent: DataForSeoBot
User-agent: MegaIndex
Disallow: /

# -------------------------------------------------------------- bad bots ----
# Bytespider: aggressive scraper, ignores rate norms. PetalBot: Huawei search,
# no relevant audience. SeznamBot: Czech search. ZoominfoBot: contact-scraping.
User-agent: Bytespider
User-agent: PetalBot
User-agent: SeznamBot
User-agent: ZoominfoBot
Disallow: /

# ------------------------------------------------------------- everyone -----
# Default for unlisted crawlers: full access; block tracking-parameter
# duplicates and WordPress-probe paths that don't exist on this static
# stack (documents intent, cuts 404 noise).
User-agent: *
Allow: /
Disallow: /*?*utm_source=
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*msclkid=
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /.env
Disallow: /.git/

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