
Website
Connect your website so your Twin stays in sync with your published content automatically.
Connection modes
- Domain crawl — indexes all pages found under a root URL
- Sitemap — imports the URL list from an XML sitemap (
/sitemap.xml) - Individual URLs — add specific pages manually, one at a time
Multiple URLs and modes can be active simultaneously. Each is tracked and synced independently.
Automatic sync
All URL sources are re-crawled every 24 hours. If your content changes more frequently, trigger a manual sync from the Knowledge Base tab at any time.
Pages behind authentication (login required) cannot be crawled. Use the Files or Text source for private content.