Training guide: web pages and subpages
In the agent's **Training** tab, the **Page scraping limit** field defines how many pages on your site the agent can access to extract information.
Pages are the main links you provide, for example:
www.yourcompany.com/productswww.yourcompany.com/about
Each link you enter is one page read by the AI.
Subpages are the internal links within those pages, for example:
www.yourcompany.com/products/product1www.yourcompany.com/about/history
Depth control
In addition to the total page limit, you set how deep the AI navigates into subpages:
- Depth 1 — accesses only the direct links on the main page.
- Depth 2 — accesses the links of those links (subpages of subpages).
Higher depth means more content processed. Use this control to avoid unnecessary reads and reduce processing time and cost.