To generate AI knowledge bases articles, I understand the agent scans the conversation data associated with those tickets from closed tickets. It does not analyze the Ticket Description property nor the breeze summary, nor the attachements.
For us most knowledge lives in test reports, drawings, application guides, certification documents, assessment reports not in tickets themselves.
We would need attachments associated with ticket conversations (including PDFs, Word files, screenshots, test reports, drawings, and other technical documents) as article-generation sources.