Skip to main content
A Run is one execution of an Agent. Use duvo runs to start Runs, check status, stream messages, respond to human-in-the-loop requests, and stop active Runs.

Starting and inspecting Runs

For teams using Automations, use --automation <automation-id> to list only Runs whose Agent belongs to that automation.
Use --since and --until to list Runs that completed in a fixed window. The --since bound is inclusive, and the --until bound is exclusive.
Add --json to any command for machine-readable output suitable for scripting.
Add --count-only when you need the matching total without Run rows. All Run filters still apply.

Streaming a Run live

Add --follow to watch messages stream in real time instead of polling duvo runs get. It works two ways:
--follow keeps printing new messages until the Run completes, then exits.

Mid-run interaction

Send a message to a Run in progress (for example, to add clarifying instructions):

Responding to human-in-the-loop requests

When an Agent pauses to ask a human a question or request approval, you can respond from the CLI:
The --answer flag takes a <question-id>=<answer-text> pair. Find the <question-id> by running duvo runs messages <run-id> and looking at the pending human request.

Scripting examples

Start a Run and wait for it to finish

Auto-approve any pending human requests on a Run

Useful in trusted batch pipelines where every approval is expected to pass:

Forward Run output to a script

Managing Agents

List and configure the Agents you can start

Cases and Queues

When Runs are kicked off by Cases on a Queue