Skip to content

Websites

Open in workspace →

Scrape and index your website content so the AI assistant can reference it when answering questions.

  1. Navigate to AI > Websites in the dashboard.
  2. Click Add Source.
  3. Enter a name and the URL to scrape.
SettingDescription
NameDisplay name for this source (max 50 characters)
URLPage URL to scrape (must be http or https)
Sync frequencyHow often to re-crawl: Never, Once a day, Once a week, or Once a month
Crawl websiteWhen enabled, crawls the entire site instead of a single page
Exclude pathsPath patterns to skip when crawling (e.g. /blog*, /login)

When Crawl website is enabled, the URL must be a bare domain (e.g. https://example.com). You can add up to 20 exclude path patterns, each supporting a trailing * wildcard.

Each source shows its current status: Draft, Pending, Indexing, Live, Warning, or Error. Content is split into chunks and indexed for semantic search.

  • Re-sync — re-crawl the page to update content.
  • Delete — remove the source and its indexed content.