Monitor & Review
Item status reporting
At the top of the Items list, status cards show a live count of items by status — how much work is in progress, waiting on review, complete, or failed.
Permissions. The Items list, and these cards, are available to users who can view items — the Reviewer role (its main workspace) and Admins. See Users and access.
The four status cards
- In Progress — the Agent is actively processing the item.
- Review — the Agent has paused the item and is asking a person to review it. See Human review.
- Complete — the Agent finished processing the item successfully.
- Failed — the Agent hit an error and stopped before finishing.
A card's count is the number of items currently in that status, so the four together tell you how the AI Agent's work is distributed right now.
What the counts represent
- Counts are for the current AI Agent, and match whatever filters you've applied to the list — filter by status, reviewer, flow, date, or search, and the cards recount to match.
- Counts reflect all matching items, not just what's on screen, and refresh when the list loads (not live) — reload to update them.
Relation to the API
These same statuses are also exposed through the API.
Where to go next
- Human review — act on items in the Review status.
- Run history — read the error behind a Failed item (Admin or Partner).
- Monitor and Review — how item status fits the production operating model.
- Users and access — who can view items and reviews.
Last modified on