- Getting started
- UiPath Agents in Studio Web
- UiPath Coded agents
Agents user guide
Running the agent
After publishing your agent from Studio Web, you can run it directly as an Orchestrator job or incorporate it into Studio workflows. Using agents in workflows lets you use them in larger deterministic processes, run multiple agents in series, and trigger execution based on events.
To incorporate your agent into a Studio workflow:
- Publish your agent to Orchestrator.
- In Studio, use the Run Job activity to integrate your agent into a workflow.
- Whenever you make changes to your agent, republish the updated agent to Orchestrator and upgrade the corresponding process in Orchestrator. The Run Job activity always executes the version of the agent configured in Orchestrator. This ensures that your workflow consistently uses the most up-to-date version of your agent.
Refer to the System activities guide to learn how to configure and use the Run Job activity in your Studio workflows.
Starting with UiPath.System.Activities version 25.4.2, the execution of agents and other Orchestrator jobs has been consolidated and improved under the Run Job activity. Existing workflows using the Run Agent activity continue to function without changes, ensuring a smooth transition. When adding new agent-running functionality to your workflows, the system automatically suggests and implements the Run Job activity, even if you search for Run Agent.
Monitoring execution
From Orchestrator, you can view inputs, outputs, tool calls, and traces for each run. Agent runs move through the following states: running, pending, suspended, completed, or failed.
Traces are the main way to understand what an agent did during a run. The traces UI surfaces:
- LLM calls and responses
- Tool invocations and results
- Errors and guardrail actions
For more information about the execution model that powers agent runs, see Running agents.