# ============================================================ # robots.txt — imagenehealth.com # Last updated: 2026-07-23 — Phase 1 SEO/GEO foundation (revised) # Source of truth: src/app/app.routes.ts # ============================================================ # ----- Default policy (search engines + all unspecified bots) ----- User-agent: * Allow: / # Authenticated platform routes (canActivate: authGuard) — never index Disallow: /home-user Disallow: /home/profile Disallow: /home/apps Disallow: /roles-permissions Disallow: /register-patient Disallow: /patient-list Disallow: /patient-summary Disallow: /test-lifecycle Disallow: /test-request Disallow: /test-request-list Disallow: /manage-users Disallow: /manage-entities Disallow: /manage-tests Disallow: /insights Disallow: /pharma-programs Disallow: /coupons Disallow: /coupons-list Disallow: /orders Disallow: /imagene-records Disallow: /imagene-records-list Disallow: /distributors Disallow: /distributor-balance Disallow: /distributor-creator Disallow: /distributor-self-register Disallow: /distributors-payouts Disallow: /my-balance Disallow: /delegated-payment Disallow: /log-viewer Disallow: /report-composer Disallow: /system-version Disallow: /construction Disallow: /consentimiento-informado # Auth flow routes — also never index Disallow: /login Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /verify-account Disallow: /complete-registration # Internal/debug routes — not for indexing Disallow: /logo # AR business-card landing (/ar/:slug) — personal QR destinations, client-rendered, # duplicate content across slugs. Not for indexing. Disallow: /ar/ # ----- AI Training bots — DISALLOW ----- # Genomic and medical content should not train commercial LLMs without # compensation or attribution. AI *search* crawlers (OAI-SearchBot, # PerplexityBot, ClaudeBot, etc.) are intentionally not listed here — they # inherit the default policy above, so they can cite public pages while the # platform routes stay blocked. Note: Google-Extended and Applebot-Extended # block training-data use only; Googlebot/Applebot search indexing is unaffected. User-agent: Applebot-Extended Disallow: / User-agent: GPTBot Disallow: / User-agent: Google-Extended Disallow: / User-agent: anthropic-ai Disallow: / User-agent: cohere-ai Disallow: / User-agent: cohere-training-data-crawler Disallow: / User-agent: CCBot Disallow: / User-agent: FacebookBot Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: meta-externalagent Disallow: / User-agent: Bytespider Disallow: / User-agent: Diffbot Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: PetalBot Disallow: / User-agent: TimpiBot Disallow: / User-agent: omgili Disallow: / User-agent: omgilibot Disallow: / User-agent: Webzio-Extended Disallow: / User-agent: YouBot Disallow: / # ----- Sitemap ----- Sitemap: https://www.imagenehealth.com/sitemap.xml