Agents user guide

Last updated Feb 19, 2026

Getting started with conversational agents

This guide walks you through building your first conversational agent: a simple HR assistant that answers questions about company policies using document search.

Prerequisites

Before you begin, ensure you have:

Access to Studio Web
An Orchestrator folder with:
- An unattended robot assigned
A Context Grounding index with your knowledge base documents

Tip:

If you don't have a Context Grounding index yet, you can still complete this tutorial. Your agent will respond based on its general knowledge.

Step 1: Create the agent

Go to studio.uipath.com.
Select Create New, then select Agent.
Select Conversational.

Create new conversational agent dialog

Describe your agent to Autopilot to generate a starter configuration. For example: "An HR assistant that helps employees find information about company policies, benefits, and onboarding procedures." If you prefer not to use Autopilot, select Start fresh.

Step 2: Configure the system prompt

The system prompt defines your agent's persona and behavior. A well-crafted prompt helps the agent respond consistently and appropriately.

In the System prompt section, define your agent's identity and guidelines. For example:

You are a friendly HR assistant for Contoso Corporation. Your role is to help employees find information about company policies, benefits, and HR procedures.

Guidelines:
- Always be professional and helpful
- If you don't know the answer, say so
- When citing policies, reference the specific document name
- Keep responses concise but complete
You are a friendly HR assistant for Contoso Corporation. Your role is to help employees find information about company policies, benefits, and HR procedures.

Guidelines:
- Always be professional and helpful
- If you don't know the answer, say so
- When citing policies, reference the specific document name
- Keep responses concise but complete

Select the Model for your agent. Different models offer varying capabilities and performance characteristics.

System prompt configuration

Step 3: Add tools

Tools give your agent the ability to take actions and retrieve information. For this HR assistant, add the Context Grounding index you previously configured as a Context tool.

Select Add context.
Select your HR documents index.
Provide a description. For example:

Provides information about company policies, benefits, and HR procedures.
Provides information about company policies, benefits, and HR procedures.

(Optional) Add additional tools such as:
- Analyze files: Allow users to upload documents for analysis.
- Integration Service connectors: Connect to external systems like calendar or email.

Tool configuration

For detailed tool configuration options, refer to the Design section.

Step 4: Test in Debug chat

Before publishing, test your agent to ensure it behaves as expected.

Select Debug then Save & Debug to open the chat interface.
Send a test message, such as: "How many holidays do we have in the US?".
Review the agent's response and check citations (if using Context Grounding).
View the execution trace in the History tab to see:
- LLM calls and responses
- Tool calls with arguments and outputs

Debug chat interface

If the response is good, select Add to evaluation set to save this conversation for future testing.

Step 5: Publish and deploy

Once you're satisfied with your agent's behavior, publish it to make it available to users.

Select Stop in the top toolbar to stop debug execution.
Rename your Solution and Agent in the Explorer to "HR Assistant".
Select Publish in the top toolbar.
Choose "Orchestrator Tenant" as the Location.
Select Publish.

Publish dialog

The publish process will begin and you will receive a message once the package is ready to be deployed.

Select Check package in the message.
Select Deploy package (rocket icon on the far right).
Choose the target Orchestrator folder (must have unattended robot account assigned).
Select Activate immediately.
Select Deploy.

Your agent is now published and deployed and available through Instance Management.

Step 6: Access your agent

After publishing, you can interact with your agent in several ways:

Instance Management: Go to Agents > Deployed agents in Automation Cloud and select Chat on your Conversational agent.
Autopilot for Everyone: Access your agent from the Autopilot picker dropdown.
Teams or Slack: If configured, interact with your agent through the Autopilot plug-in.

Instance Management

You've built and deployed your first conversational agent. To learn more:

Design: Configure advanced options like escalations, agent memory, and model selection
Evaluation: Create comprehensive test suites for your agent
Observability: Monitor performance and collect user feedback
Licensing: Understand consumption and pricing for your deployment

On this page