Messages

The Messages page is your operational view into everything Mary has handled. It shows every processed reply, the category she assigned, and — if you click in — exactly why she classified it that way and what actions she fired. This is where you go when you want to confirm the system is working, debug a specific reply, or audit a category’s behavior after a prompt change.

​

The message feed

Processed emails are displayed as cards showing:

• The email subject line
• The sender’s name and email address
• The category Mary assigned (e.g., → Human Request)

Cards are listed newest-first by default.

​

Filtering by category

Use the tab bar at the top to slice the feed by category. Click Unsubscribe to see only unsubscribe replies, Bounce for bounces, and so on. Recents shows the most recently processed emails regardless of category. Filtering is the fastest way to spot-check a category after you’ve edited its prompt — open the tab, scan the recent matches, and confirm they all look right.

​

Inspecting an individual email

Click any message card to open the detailed view. The detail panel is structured around the full processing pipeline, so you can see exactly what happened at each step. The top of the panel shows:

• The full email body as it arrived
• The classification Mary assigned and her plain-English reasoning for why she made that call

Below that, expandable sections walk through the rest of the pipeline: This view is the single best debugging tool when something looks off — you can see Mary’s reasoning, the values she extracted, and the result of every action she fired, all in one place.

​

Re-running a misclassified email

If you spot an email that was classified incorrectly, you don’t have to wait for a similar reply to arrive again to test your fix. Click Re-run on the detail view and Mary will reprocess the email using your current category configuration. This is the standard workflow for tightening up a category prompt: