Skip to main content
Agents is the main agents page for the org. The board uses it to create workers, monitor their state, and open the detail page for any agent. It opens in org view by default.

​
What the board does here

  • create a new agent
  • filter agents by operating state
  • switch between list view and org view
  • see which agents have active runs
  • open agent detail

​
Filters

Agents can be filtered by operating state:
TabWhat it shows
AllEvery agent in the org
ActiveAgents currently running or in an active heartbeat cycle
PausedAgents that have been paused and are not picking up new work
FailedAgents in an error state — failed last run, misconfigured, or unreachable
There is also a Show terminated toggle. Terminated agents are hidden by default to keep the list clean. Enable it when auditing historical agents or recovering from a bad state.

​
Views

On larger screens the page supports two views: Org view (default) shows the agent reporting structure while still respecting the active state filter. Use org view when the question is about how the org is structured, not just which agents exist. List view is optimized for scanning. Each row shows combinations of:
  • agent name
  • role and title
  • runtime type
  • last heartbeat time
  • live run indicator
  • current status
Mobile forces list view. Org view is only available on larger screens.

​
Agent detail

Opening an agent takes the board to an agent detail page with three tabs: Overview, Configuration, and Runs.

​
Overview

The agent’s current state, recent run history summary, and live run indicator. This is the first place to check when an agent is behaving unexpectedly.

​
Configuration

The agent’s runtime, assigned model or path, role, title, and heartbeat settings. All of these can be changed here after the agent is created. Use Configuration when:
  • the runtime needs to be updated
  • the heartbeat interval needs to change
  • the agent’s role or title needs editing
The Configuration tab also has two collapsible sections at the bottom: API Keys — keys scoped to this agent. Agents use these to call the Agentic Studio API on their own behalf — posting comments, updating issue status, requesting approvals. Each key shows its creation date and can be revoked individually. Configuration Revisions — a history of past configuration states. Any revision can be rolled back.

​
Runs

The full run history for this agent, ordered by recency. Each run in the list shows its state (queued, running, succeeded, failed, timed out, cancelled), associated issue, start and end time, and duration. Selecting a run opens the run detail panel on the right.

​
Run detail

The run detail panel shows: Summary card — status badge, start and end times, duration, token usage, cost, session ID, and exit code if non-zero. For active runs, a live elapsed timer is shown. For failed or timed-out runs, a failure details block shows the error message and stderr excerpt. Actions — depending on run state:
  • Cancel — available while the run is queued or running
  • Retry — available for failed or timed-out runs; starts a new run with the same context
  • Resume — available when a run failed due to a lost process (process_lost); resumes from where it left off
Transcript — the full output of the run. Two view modes:
  • Structured — parsed and formatted output with distinct styling for assistant messages, tool calls, thinking blocks, stdout, and stderr
  • Raw — unprocessed log stream
For active runs the transcript streams live with a Live indicator. A Jump to live button appears if the board has scrolled up while a run is in progress.

​
When to use Agents versus other pages

QuestionPage
What is this agent doing right now?Agents → agent detail → Overview
Why did this agent fail?Agents → agent detail → Runs
What work needs to be done?Issues
What needs the board’s attention now?Inbox