Add your website as a knowledge source
Enter your URL
Type or paste your website’s root URL — for example,
https://yourcompany.com. InsiteChat starts from this page and follows links to discover the rest of your site.What gets indexed
InsiteChat follows links from your starting URL and indexes every page it can reach, including:- Product and service pages
- Blog posts and articles
- FAQ and help center pages
- About, pricing, and contact pages
robots.txt are not crawled.
Crawl depth and what to expect
InsiteChat crawls your site up to several levels deep, following internal links automatically. For most sites, the full crawl completes within a few minutes. Very large sites may take longer. The crawler extracts the main text content from each page. It does not index images or embedded videos — for that content, use Document Upload or add a YouTube transcript as a separate source.Keep your content up to date
Your website content changes over time. InsiteChat provides two ways to re-sync a crawled source so your chatbot stays current.Manual sync
You can trigger a sync at any time on all paid plans:Auto-sync
InsiteChat can re-sync your website automatically based on your plan:| Plan | Auto-sync frequency |
|---|---|
| Free | No auto-sync |
| Starter | Monthly |
| Growth | Weekly |
| Scale | Every 3 days |
On every sync, InsiteChat only re-processes pages that have changed since the last crawl. Unchanged pages are not re-indexed, so syncs are fast and efficient.
