Follow, pause, stop and retry a long AI Agent run
Long AI Agent work runs in the background, so you can leave the page: "You can leave this page; the answer will be here." The run panel in the chat shows the step it is on ("Step 2 of 5"), the time used, and "Changes made so far: 1 change".
Read a run's status
| Run status | Meaning |
|---|---|
| Queued | About to start. |
| Running | Working now. |
| Waiting for you | Needs your OK or an answer in the chat. |
| Waiting for a job to finish | Waiting on a pipeline job. |
| Resumes at 9:00 AM | A step waits until a set time. |
| Pausing…, Paused | You paused it. It stops after the call in progress. |
| Out of time | It used its time budget. |
| Done, Failed, Stopped | How the run ended. |
In the chat list, a chat's line shows where its work stands: Working…, Waiting for your OK, Needs your answer, Paused, Out of time, Failed or New result.
Other steps the assistant took lists lookups ("Lookup, nothing changed") and edits ("Edited something") made outside the plan's steps.
Pause, resume, add time or stop a run
| Control | When you see it | What it does |
|---|---|---|
| Pause | While it runs | Holds the run after the current call. |
| Resume | While paused | Carries on. |
| Add time | Out of time | Gives the run more time and starts it again. |
| Retry | Failed | Runs it again. |
| Stop | While it runs | Ends the run. "Stopped. Finished steps stay done." |
| Continue | After a stop | Carries on from where it stopped. |
Stop on the plan card or the run panel ends the work part way; finished steps stay done. The card then says "Stopped part way. Continue where it stopped?" with Leave it as it is and Continue.
Track batch items in a run
When a run works through many items, Items (24) lists each with its state: Done, Failed, Queued, Running or Already gone.
- You see progress ("10 of 24 done") and an estimate, for example "about 4-6 min left".
- Retry on a failed item runs it again.
- If the estimate runs past the budget: "This may not finish within the time budget. You can Extend it." Use Add time when the run reaches Out of time.
Get a browser alert when a run finishes
Where the chat says the work moved to the background, click Alert me in the browser when it's done. Your browser asks for permission once; then you see "You'll get a browser alert when it's done." The option is hidden if your browser blocks notifications for Mammoth.
Fix a failed step
A failed step says why, for example "Failed at step 3 of 5".
- Try again or Ask agent to fix puts a fix request in your message box, starting "Fix what wasn't built:" with each failure listed. Edit it if you like, then send.
- Retry on a failed run runs it again.
Neither button sends anything on its own: you review the message and send it.
Undo what the agent changed
The chat's cards have no Undo for changes to your data. To take back a change to a view, use the Data Editor (see How the pipeline works). Objects the agent made can be deleted like any other, and deleted items go to Trash (Get things back from Trash). If a change was undone, its card shows Undone.
Related
- Plans and runs: what waits for your OK and how to approve it.
- Results, charts and canvases: what the agent shows when the work is done.
- Find, share and delete chats: the status dots in the chat list.
Something wrong? support@mammoth.io