User Manual
Running Agents
How to start a run, follow it on the Runs page, read its trace and confidence score, and tell when it has been flagged for your review.
Your agents
Each agent handles one kind of work and sends a decision to your Inbox only when it is beyond what the agent is allowed to decide. There are department agents such as Finance, HR, Legal, Sales, Operations, Security and Audit, and narrower specialists such as the AP Specialist, the Contract Reviewer and the Payroll Processor.
Starting a run
The quickest way to run your first agent is the Get started flow. It walks you through creating an API key, connecting an integration and starting a run.
- •
Pick an agent type
Choose the specialist for the job, for example AP Specialist, Contract Reviewer or Inventory Monitor. - •
Describe the task
Describe the task in plain language in the task field, for example “Review this supplier agreement and list the payment terms”. - •
Run it
Start the run. Its status updates on the page as it goes.
The Runs page
Runs lists every agent run newest-first, with three header stats and a filterable table. The header status line shows how many runs are live and the total count.
Header stats
| Total Runs | Every run dispatched in your workspace. |
| Currently Running | Runs in progress right now (pulses blue when active). |
| Awaiting Triage | Runs flagged for a human decision. |
The table
Each row shows the agent type, the task, the status, and the confidence score. You can filter the list by status (for example running or failed) and by agent. Runs that need a decision are flagged for triage and also appear in your Inbox.
Reading a run trace
Open any run to see its trace. The run detail page shows the agent, a status badge, the duration and completion time, and the original Task. When they exist, it also shows the Confidence Score, the structured Result, the agent's Reasoning, its Proposed Approach, Validator Notes, any error message, and the tokens used.
Confidence score
The confidence score is shown as a percentage with a label. A run needs 85% or more to proceed without review:
| 85% and above | High confidence |
| 65–84% | Moderate confidence |
| Below 65% | Low confidence |
requires_triage
When a run needs a human decision it is marked requires_triage. The detail page then shows a “Sent to Human Review” banner with the triage reason and a Review in Inbox → link. The usual causes are low confidence and a broken rule.
Worked example: a low-confidence contract review
Example · When a run routes itself to your Inbox
You run a Contract Reviewer on a new supplier agreement. The agent extracts the key terms but returns a 58% confidence score because an indemnity clause is ambiguous. That is below the threshold, so the run is marked requires_triage.
- On Runs, the row shows status Triage Required and the 58% score.
- On the run's detail page, the Sent to Human Review banner explains why.
- In your Inbox, the item appears with the agent's reasoning so you can decide.
You read the clause and approve or reject from the Inbox, and the run finishes accordingly.