How to Build an AI Agent in UiPath (Step-by-Step Tutorial)

Kevin Stratvert · Beginner ·🤖 AI Agents & Automation ·2w ago

Key Takeaways

Builds an AI agent in UiPath from scratch

Original Description

In this step-by-step tutorial, you'll learn how to build an AI agent in UiPath from scratch. We'll start in the command line using the UiPath CLI, create an agent project, configure the agent with JSON, validate and deploy it, and then bring it into UiPath Studio Web for testing and refinement. Bring Claude Code, OpenAI Codex, Google Gemini CLI, Cursor, or any coding agent on UiPath, try for free: http://uipathaiagents.kevinstratvert.com Along the way, you'll learn how agent inputs and outputs work, how to define prompts and schemas, how to debug your agent, and how to improve performance using evaluation tools. We'll also compare the code-first and visual approaches to agent development in UiPath. Whether you're new to AI agents or looking to build production-ready automations with UiPath, this tutorial will help you get started. Host: Kevin Stratvert Sponsor: UiPath 📚 RESOURCES - Download Visual Studio Code: https://code.visualstudio.com - Get Node.js: https://nodejs.org - Build Your First UiPath Automation (AI + RPA + Human Approval): https://youtu.be/p0AfPMV3BWw 🚀 COMMANDS https://docs.google.com/document/d/1UcS3-QVj9P8ooI_11hDtZm2OtPQjK7GLOvkFFiooDZM/edit?usp=sharing ⌚ TIMESTAMPS 00:00 - Introduction 00:52 - What we're building 01:29 - Install the UiPath CLI 02:36 - Install the agent tools 02:49 - Optional: Install UiPath Skills for Coding Agents 03:27 - Authenticate with UiPath 03:44 - Create a solution and agent project 04:46 - Configure agent.json and entrypoints.json 07:20 - Validate the agent 07:47 - Upload the solution to Studio Web 08:15 - Open the agent in Studio Web 08:38 - Test the agent with sample inputs 09:42 - Evaluate and Improve Your Agent 10:05 - Build Visually or with Code 10:34 - Wrap up 📺 RELATED VIDEOS - Playlist with all my videos on UiPath: https://www.youtube.com/playlist?list=PLlKpQrBME6xIIEoyVO3IgDU1gKF1h0SGl 📩 NEWSLETTER - Get the latest high-quality tutorial and tips and tricks videos emailed to your inbox each week: htt
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related Reads

📰
OpenAI tries the consulting path with 'Presence', charging enterprises boots-on-the-ground prices to deploy agents
OpenAI's 'Presence' offers enterprises on-site AI agent deployment for a premium price, highlighting a shift towards consulting services in the AI industry
The Register
📰
What is a Ralph Loop?
Learn about the Ralph Loop and how it affects agent workflows, and why it matters for efficient AI development
Dev.to AI
📰
building enterprise multi-agent workflows in .net with mistral
Learn to build enterprise multi-agent workflows in .NET using Mistral's Agents API for stateful conversations and task automation
Dev.to AI
📰
Automation Is Evolving Beyond RPA: Why AI Agents Are the Next Enterprise Leap
Learn how AI agents are evolving automation beyond RPA, enabling enterprises to adapt to dynamic business processes and make informed decisions
Dev.to AI

Chapters (15)

Introduction
0:52 What we're building
1:29 Install the UiPath CLI
2:36 Install the agent tools
2:49 Optional: Install UiPath Skills for Coding Agents
3:27 Authenticate with UiPath
3:44 Create a solution and agent project
4:46 Configure agent.json and entrypoints.json
7:20 Validate the agent
7:47 Upload the solution to Studio Web
8:15 Open the agent in Studio Web
8:38 Test the agent with sample inputs
9:42 Evaluate and Improve Your Agent
10:05 Build Visually or with Code
10:34 Wrap up
Up next
6 Agentic AI Projects: Every AI Engineer Needs in 2026
Rajeev Kanth | BEPEC
Watch →