UiPath Documentation
getting-started
latest
false
Getting started developer guide
  • Introduction
    • Overview
    • Environment set up
  • Getting Started with UiPath Agents
  • Getting Started with UiPath Agents using LangGraph
  • Building a Low-Code Agent in Studio Web
    • Introduction
    • Build the agent
    • Test the agent
    • Evaluate the agent
  • Adding Tools to Your UiPath Agent
  • Getting Started with the Flow canvas in UiPath Maestro

Introduction

Build a low-code quest classifier in Studio Web using Autopilot, test it, and evaluate it, with no CLI, no code, and no IDE required.

In this lab, you build a low-code agent entirely in the UiPath Studio Web browser interface, with no command-line interface (CLI), code, or integrated development environment (IDE) required. The lab covers these steps:

  1. Create a new agent project in Studio Web.
  2. Generate the agent configuration using Autopilot.
  3. Review and refine the system prompt, input, and outputs.
  4. Test the agent live in the Debug panel.
  5. Save your test runs as an evaluation set and score the agent against it.

There are three approaches to create UiPath agents. This lab explores the Agent Builder project within Studio Web; you can also create agents using the UiPath CLI. The LangGraph lab builds this same quest classifier as a coded agent in Python, so you can compare the two approaches side by side.

Estimated time: 25-30 minutes

What you are building​

This lab builds a quest intake classifier, a low-code agent for a fictional Adventurer's Guild in a fantasy role-playing game world. Given a quest description, the agent sorts the quest into one of four difficulty tiers and explains its reasoning.

ComponentDetails
System promptQuest intake classifier that sorts a quest into exactly one of four difficulty tiers
Input: questDescriptionstring; the quest description
Output: tierstring; exactly one of Trivial, Standard, Heroic, or Legendary
Output: reasoningstring; a brief, two-sentence explanation of the classification
Evaluation setTest cases saved from your own debug runs, scored with a semantic similarity evaluator

Prerequisites​

No CLI, SDKs, or local tooling is needed for this lab.

  • What you are building​
  • Prerequisites​

Was this page helpful?

Connect

Need help? Support(opens in new window)

Want to learn? UiPath Academy(opens in new window)

Have questions? UiPath Forum(opens in new window)

Stay updated