Skip to main content
Training your chatbot on your website content is the most common way to get started with SiteSpeakAI. You can either crawl an entire website or add specific page URLs.

​
Website Source

Use the Website option to automatically crawl and discover pages from your website.
1

Go to Training & Content

In your chatbot dashboard, click Training & Content in the sidebar.
2

Select Sources

Click on Sources.
3

Click Add Sources

Click the + Add Sources button.
4

Select Website

From the source type dropdown, select Website.
5

Enter your website URL

Enter your website URL in the Website URL field.
6

Crawl Website

Click the Crawl Website button. SiteSpeakAI will scan your website and discover available pages. This may take a minute or two depending on the size of your website.
Website source input

​
Selecting Pages to Train

After crawling, you’ll see a list of discovered pages with their URLs and content sizes.
1

Review discovered pages

Browse the list of pages found on your website.
2

Select pages

Use the checkboxes to select which pages you want to train your chatbot on. You can select all or choose specific pages.
3

Add Selected

Click the Add Selected button to add the chosen pages as training sources.
List of discovered website pages
Focus on pages with valuable content like product pages, FAQs, help articles, and documentation. Skip pages with minimal content like login pages or utility pages.
Use the Links option to add specific page URLs directly, without crawling an entire website.
1

Go to Training & Content

In your chatbot dashboard, click Training & Content in the sidebar.
2

Select Sources

Click on Sources.
3

Click Add Sources

Click the + Add Sources button.
4

Select Links

From the source type dropdown, select Links.
5

Enter your URLs

Enter the page URLs you want to train on in the Link URLs field. Separate each link by a new line.
6

Fetch Links

Click the Fetch Links button to retrieve the content from each URL.
Link source input
After fetching, you’ll see each URL with its content size.
1

Review fetched links

Check the list of URLs and their content sizes.
2

Select links

Use the checkboxes to select which links you want to train on.
3

Add Selected

Click the Add Selected button to add the chosen links as training sources.
List of fetched link pages
Use CaseRecommended Option
Train on your entire websiteWebsite
Train on specific pages onlyLinks
Add pages from multiple different websitesLinks
Discover pages you might have missedWebsite
Add a single blog post or articleLinks

​
Managing Your Trained Sources

After adding sources, they’ll appear in your Sources list with their training status.
Trained sources list
Each source shows:
  • Name: The page title
  • URL: The source URL
  • Type: Link icon for web sources
  • Size: Content size (e.g., 5.8 KB)
  • Status: Training status (Trained, Training, Pending, Error)
  • Auto: Whether auto-sync is enabled
  • Last Trained: When it was last processed

​
Keeping Content Updated

To update your trained content when your website changes:
1

Select sources

Use the checkboxes to select the sources you want to update.
2

Click Retrain

Click the Retrain button to re-fetch and retrain on the latest content.
Enable Auto Sync on important sources to automatically keep them updated.

​
Best Practices

  • Start with key pages: Train on your most important content first (FAQs, product pages, documentation)
  • Review content quality: Ensure pages have meaningful text content, not just images or videos
  • Remove duplicates: Avoid training on multiple pages with the same content
  • Update regularly: Retrain sources when your website content changes significantly

Ready to automate your customer service with AI?

Join over 1000+ businesses, websites and startups automating their customer service and other tasks with a custom trained AI agent.
Last modified on January 28, 2026