/command-center).
Use it when you need to approve human tasks, pause or stop runs, or triage recent failures — without opening every workflow in Workflow Studio.
What you see
Command Center organizes runs into four sections:
The page header shows badges when action is needed:
- N pending — human tasks waiting for approval
- N draining — graceful stops still winding down
Awaiting approval
When a workflow hits ahuman_task step, the run pauses and tasks appear here grouped by workflow and run.
For each pending task you see:
- Workflow name and run ID (first 8 characters)
- Task type (for example,
approval) - Step ID that triggered the pause
Approve or reject
1
Review the task
Read the task type and step ID. For full payload context (draft email, proposed data changes), click Review in studio to open Workflow Studio on the run context tab.
2
Decide
Click Approve to continue the run with an approval result, or Reject to stop the branch with a rejection result.
3
Confirm the run resumes
After approval, the task disappears from Command Center and the run continues. Check Running now or open the run in Studio to watch downstream steps.
Approve/reject here is the same action as completing a task in Workflow Studio or via
POST /v1/workflows/{id}/runs/{runID}/tasks/{task_id}/complete. See Human tasks.Running now
Active runs appear with status badges:Run controls
From Running now (and Stopping gracefully), you can:
Click Open run to jump to Workflow Studio’s event log for that run.
Stopping gracefully
When you choose graceful stop, the run moves to Stopping gracefully until all in-flight steps complete. The badge reads Draining. If a drain takes too long, escalate to immediate stop from the same row. A drain timeout surfaces asDRAIN_TIMEOUT in the failure log.
Failed recently
Runs that failed or were stopped in the last 24 hours appear here. Open the run in Workflow Studio to read step-level error messages andfailure_code values.
Common failure codes:
See Troubleshooting for recovery steps.
When a run looks stuck
Work through this checklist:- Check status in Command Center — Is it
paused,draining, or waiting on approval? Complete the human task or resume if paused. - Open the run in Studio — Read the event log for the last step started. A step stuck in
runningmay be waiting on a slow MCP call or LLM response. - Try pause then stop — Pause prevents new steps. If still stuck, use immediate stop.
- Check connections — MCP binding failures often show as
MCP_TOOL_FAILEDon the first tool step. See Troubleshooting. - Check credits —
INSUFFICIENT_CREDITSblocks new runs and can fail in-flight billing gates.
API equivalents
Related docs
- Runs and observability — run lifecycle, failure badges
- Run recovery (roadmap) — planned continue-from-failure
- Human tasks — authoring approval gates
- Workflow patterns — approve-then-send and error handling