Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Building AI Agents with smolagents
Rating: 4.5 out of 5(36 ratings)
1,107 students

Building AI Agents with smolagents

Understand theory of AI agents and how to build them with smolagents library
Created byJohannes Hayer
Last updated 5/2025
English

What you'll learn

  • Understand AI agent theory - how agents differ from LLMs, their components (brain/body), and when to use agents vs workflows for different tasks.
  • Build multi-agent to solve complex problems with specialized agents
  • Build AI agents with smolagents that can search the web, process data, and execute code, plus create custom tools to extend agent capabilities.
  • Build agents with GradioUI interfaces, share on Hugging Face Spaces, and implement monitoring with OpenTelemetry and LangFuse for production use.

Course content

4 sections20 lectures1h 36m total length
  • Course Goal1:05
  • Resources0:02

Requirements

  • Basic Python programming knowledge. Some familiarity with LLMs is helpful but not required. You'll need a computer with Python installed and a free Hugging Face account.

Description

What you'll learn:

  • Build AI agents that interact with external systems and tools

  • Understand the architecture of modern AI agent systems

  • Implement single agents and multi-agent collaboration patterns

  • Create custom tools for your AI agents

  • Add user interfaces with GradioUI

  • Deploy agents to Hugging Face Spaces

  • Set up monitoring with OpenTelemetry and LangFuse

Course Description:

Move beyond basic chatbots and build AI systems that take real actions in the world.

This course takes you from AI agent theory to implementation using the smolagents framework. You'll learn to build systems that search the web, process data, execute code, and collaborate with other agents.

We begin with theory, explaining the differences between traditional LLMs and AI agents, agent architecture, and when to use workflows versus agents. You'll understand the spectrum from developer-controlled flows to autonomous agents.

Then we dive into hands-on development. You'll build your first agent, create custom tools, implement user interfaces, and deploy to Hugging Face Spaces. The course concludes with multi-agent systems and monitoring techniques.

By the end, you'll have the knowledge and skills to design, build, and deploy AI agent systems for various applications.

Requirements:

  • Basic Python programming knowledge

  • Familiarity with LLM concepts

  • No prior experience with AI agents required

Who this course is for:

  • Software developers adding AI capabilities to applications

  • Machine learning engineers expanding beyond traditional models

  • AI enthusiasts building interactive systems

  • Professionals automating complex workflows

  • Students and researchers exploring AI applications

Who this course is for:

  • Developers and AI enthusiasts who want to build AI systems that take actions beyond text generation. Perfect for those looking to create practical agents that interact with external systems.