
Compare code-based actions and json tool calls in multi-step agents, and learn why code agent actions offer better composability, handling of complex objects, and generality.
Build a multi-agent system that orchestrates web search, content analysis, and final market reports via a manager delegating to a web search agent and an analyst.
Learn to set up and use MCP servers locally with small agents, discover servers via Smithery, configure environments and API keys, and inspect tools with the inspector.
Explore ai agents with small agents, from large language model limits to brain and body architecture, workflows, multi-agent systems, weather and code agents with tool calling.
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