- Getting started
- UiPath Agents in Studio Web
- UiPath Agents in Agent Builder
- UiPath Coded agents

Agents user guide
Managing UiPath agents
The Agents page in Automation CloudTM provides a comprehensive agent management experience, offering the following capabilities:
- Migrating early adopter agents to solution packages
- Monitoring deployed agents' performance
- Identifying and addressing agent incidents
- Accessing Marketplace agent templates
This centralized hub allows real-time monitoring of all agent runtimes, with alerts for errors, health score degradation, and poor runtime evaluation scores.
Terminology
-
An Agent instance is a single deployed agent within a running business process, represented as a task in BPMN, being the live execution of an agent runtime that responds to specific triggers, queues, or other workflow conditions.
-
Agent instance management represents the set of tasks related to monitoring, maintaining, improving, and terminating agents and agent jobs.
Key features
Here are the key features of the redesigned Agents page in Automation CloudTM:
- Real-time agent monitoring using BPMN workflows.
- Error handling and recovery through BPMN-defined events.
- Runtime agent coordination between agents and human operators.
- Merging and consensus handling via decision-making gateways.
- Performance analysis and optimization based on multiple metrics.
- Governance and compliance checks ensuring adherence to enterprise rules.
The Home tab provides a broad view of agent runtime and monitoring. From here you can:
- Manage your deployed agents and monitor their performance.
- Manage and monitor your early adopter agents.
- Manage and monitor agent incidents and errors.
- Monitor the status of your indexes and their ingestion progress.
- Check out Agents templates that are available in Marketplace.
The All agents instances tab provides visibility into agents deployed to production and includes:
- Monitoring dashboards for Live Instances Timeline and Completed Instances Timeline.
- A list of Live agents:
Displays agents that executed during the selected time interval. For each agent,
key run metadata is shown. Selecting an agent opens its individual instance
view, which includes:
- A short description of the agent, including configuration, settings, and retention policies.
- A chronological list of
all job executions during the selected time interval. Selecting a job
opens a detailed trace view for that execution.
The trace view offers the following insights into each agent run: execution flow with color-coded outcomes (success, failure, retry), preview on start and end timestamps, execution status, input and output snippets, and full details on JSON payloads, logs and errors, runtime metrics, (token usage, latency). For details, refer to the following section.
Use the time filter to adjust the displayed interval: last hour, last day, last week, last month.
The trace view combines a graphical representation of the agent’s logic with time-aligned execution data, allowing you to inspect the flow and outcomes of each step. The canvas shows nodes representing major agent components like models and tools, connected in sequence.
Once you're in the Trace view of an agent run, follow these steps to interact with and investigate the trace data:
- Preview node information.
Hover your mouse over any node on the canvas to see a tooltip that includes:
- The execution status (success, retry, or failure)
- Start and end timestamps
- A preview of the input and output data
- View full node details.
Select any node to open a detailed panel which includes:
- Complete input and output payloads (JSON)
- Execution logs or error messages (if applicable)
- Runtime metrics, such as latency and token usage
- Configuration parameters, if available
- Navigate between related steps, to explore how information flowed through
the agent:
- Select connected nodes to move upstream or downstream.
- This helps you trace how decisions, inputs, or outputs from one step influenced the next.
- Use the Execution
Trace panel. This panel shows a chronological list of all recorded
actions during the agent run.
- Select a row in the trace log to highlight the corresponding node on the canvas.
- Similarly, selecting a node on the canvas automatically highlights the relevant row in the trace log.
The Early Adopter Agents tab shows all the agents you created in Agent Builder before May 14, 2025.
Select the Migrate button for each agent to migrate it to Studio. For details, refer to Migration steps.
The Errors tab enables monitoring for agents with the most errors. The tab shows:
- Agents with most errors, displayed as a chart. Use the Show dropdown menu to display either the top 5 or top 10 items, for the selected time range.
- Incidents table, with a list of agent execution incidents, including a Description column that provides quick insights into the cause of each incident. By selecting the entries in the First seen or Last seen column for an incident, you can view the job details panel for the corresponding job.
To group incidents by Agent or Parent process, select the corresponding checkboxes.
The Context grounding indexes tab enables you to monitor the status of your indexes and track their ingestion progress at the tenant level.
The Index Monitoring section provides graphical insights into the following metrics:
-
Queries: Tracks the number of queries performed on your indexes over a selected time interval.
-
Index jobs: Displays a count of ingestion jobs. If no jobs have been run in the selected time period, a placeholder graphic is shown.
The Indexes table lists all available indexes in your tenant. For more granular information on indexes, select an index from the table. The individual view provides the following information:
- The number of Queries during the selected interval.
- The index Sync job history during the selected interval. Select an entry in the sync table for a detailed view of the ingested documents.
The Templates tab provides direct access to the agent templates available in UiPath Marketplace.
To learn how to use templates, refer to Using agent templates.