Train your agent on your content

Sources give the agent the facts it can retrieve. Start with the smallest authoritative set, test it, then expand.

Add a website

1. Open an agent and select Sources.
2. Choose Crawl website, enter the site URL, and start the crawl.
3. Wait for processing to finish, then test a known question in Playground.

Use a page crawl when you need one URL rather than a whole site. Website and page ingestion require publicly reachable URLs.

Upload a file

Choose Upload file, select the document, then wait for processing. The source list shows its status; a file is not available for retrieval until processing succeeds.

Add an exact Q&A

Choose Q&A, enter the customer question and the answer you want the agent to use, then save. Q&A pairs are useful for concise policies or corrections that should not depend on a long page.

Connect Notion

First connect Notion under workspace Integrations. Return to the agent's Sources page, choose the Notion pages to sync, and add them. If the connection needs attention, reconnect it before retraining.

Keep knowledge current

• Use Retrain after the underlying content changes.
• Configure Auto retrain for recurring website refreshes.
• Remove obsolete sources so stale facts do not compete with current ones.
• Use Retrieval settings to tune how the agent searches its knowledge, then compare results in Playground.

Deleting a source removes it from future retrieval. Always rerun your highest-value test questions after a source change.