Conversations & analytics

Every conversation an AI Fellow has gets recorded automatically. From the Fellow's detail page you can see how the Fellow is being used and read what people are actually asking.

What you'll see

• Last 30 days. Active conversations, total messages exchanged, voice minutes.
• Transcripts. Full text of each conversation, exactly as it happened.

A note on privacy

How a transcript is attributed depends on the Fellow's visibility:

• Public Fellows. Conversations are anonymous. You can read every transcript from the admin panel, but the transcripts cannot be filtered by user. There's no person identity attached.
• Private Fellows. The user must be logged in, so the conversation is tied to their identity. You can search transcripts by user.
• Inside a Learning Path. The user is identified for progress tracking, so per-user progress against the program's sessions and objectives is visible to admins. The transcript itself follows the same rules as a Private Fellow.

If you need attributed progress tracking on what is otherwise a casual Fellow, switch its visibility to Private or move it into a Learning Path.