Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.encord.com/llms.txt

Use this file to discover all available pages before exploring further.

There are two ways to run Agents in Encord:
  • In the Label Editor: The Agent is triggered on demand by the Tasker while annotating or reviewing a task.
  • From your Workflow: The Agent is triggered on tasks that pass through the Workflow node.

​
In the Label Editor

All agents created via the Agents Catalog (built-in and custom) are triggered in the same way from the Label Editor:
  1. Open the data item in the Label Editor.
  2. Right-click in the editor canvas, choose Trigger agent, and select the agent you want to run.

​
In the Workflow

Agents can be added as a Workflow node when creating or editing a Workflow. When the Workflow runs, the Agent is triggered for all tasks that pass through that node.
  1. Drag the Agent node in the Workflow editor onto the canvas and connect it to the desired nodes.
  1. Click the Agent node.
  2. Click the + to add a new Agent, or the dropdown to select an existing enabled Agent.
  1. Click Run next to a task to run the Agent on a specific task to verify the output is as expected.
  2. Click Go live to automatically run the Agent on tasks that pass through this node in the Workflow.
Agent activity can be monitored in the Analytics dashboard. See Analytics for Agents for details.
If you do not have access to the Ontology required by an Agent, you see an error message with an option to join the Ontology, if you’re an Org Admin.

​
Agent Task Management

When viewing an Agent stage, the Queue displays additional controls and status information for Workflow agents. Agent Status Banner For Agent stages, a status banner appears above the task list showing the agent name and icon (click to view detailed agent configuration), a status indicator showing whether the agent is Live (green) or Paused (orange), and control buttons that Admins and Team Managers can use to pause/resume agents or view agent settings. Agent Controls
Only Workspace and Project Admins and Team Managers can control agent execution.
Click Pause to stop the agent from automatically processing new tasks, or Go live to resume automatic processing. Paused agents allow for manual task execution and troubleshooting. When an agent is paused, you can manually trigger execution for specific tasks by navigating to the paused Agent stage, finding tasks with Pending status, and clicking the Run button next to individual tasks. To retry tasks that failed during agent execution, locate tasks showing a Failed status and click the Retry button to re-run the agent on those specific tasks.
Use manual execution when testing agent configurations or troubleshooting specific data units before resuming live processing.
Agent Execution Status For Projects using Agents in their Workflow, tasks display execution status badges showing the current state of automated processing:
StatusDescription
PendingThe agent execution is queued and waiting to start.
DispatchedThe agent execution has been assigned to a worker.
RunningThe agent is currently processing the task.
SucceededThe agent execution completed successfully.
FailedThe agent execution encountered an error and failed to complete.
Timed outThe agent execution exceeded the maximum allowed time and was terminated.
CanceledThe agent execution was manually canceled before completion.
Retry Failed Tasks You can retry tasks that failed or timed out by selecting one or more affected tasks in the Queue, then clicking Retry failed to re-run the agent on those tasks. The system will attempt to execute the Agent again on the selected tasks.
The Retry failed button is only available for Agent stages with catalog agents and only appears when you have selected tasks that failed or timed out.
Moving Agent Tasks When moving agent tasks to the next stage, the system skips tasks that are currently running or dispatched (they remain in the current stage), only moving tasks that are not actively being processed. A confirmation dialog will show how many tasks are moved and how many are skipped.
Tasks that are currently running or dispatched cannot be moved and remain in their current stage until execution completes.

​
Agent Go-Live Modal

When activating a paused Agent in a Workflow, the go-live modal displays recent execution results to help you verify the Agent is working correctly before enabling automatic processing. The modal shows up to 10 execution results per page. When there are more than 10 results, pagination controls appear at the bottom of the modal, allowing you to browse through all available execution results.
Use the pagination controls to review execution results from different time periods before going live with your Agent.
You can also click the Paused status label in the Agent status banner to quickly open the go-live modal and review recent executions.

​
Agent Information Panel

When viewing an Agent’s details, you can access information about its connected Ontology. If the Agent uses an Ontology that you have access to, the Ontology name appears as a clickable button that opens the Ontology page in a new tab for easy reference.
Click the Ontology name to view the complete structure and classes used by the Agent, which can help you understand what the Agent is designed to detect or classify.