Course

AI Agents from Scratch

Through this course you'll explore how to design effective AI agents, connect AI systems with tools and external data, and build agent-powered applications. You'll gain the core concepts and practical skills needed to start creating capable AI agents, with room to expand into more advanced techniques as the ecosystem evolves. 2 of 3 modules are released.

Start learning
 
EXPERIENCE
Intermediate level
EST TIME TO COMPLETE Completion time may vary based on individual pacing.
3 hrs, 21 mins
CONTENT
2 modules

Learning path outcomes

Understand the architecture of modern AI agentsDesign effective AI systemsConnect LLMs with external tools

Prerequisites

Basic to intermediate Python proficiency. No mobile development experience necessary.

Learning path content

1
Context Engineering for AI Mar 15 2026 · Multimodal Module (1 hr, 10 mins)
Explore context engineering as the foundation for building reliable, efficient AI systems. Learn how LLMs, prompting, RAG, agents, LangChain, and LangGraph work together in real applications. Understand the AI platform ecosystem and build practical workflows to choose the right tools for real-world use cases.
Go to module
Expand module content Hide module content Show module content Hide module content
2
MCP Fundamentals Apr 10 2026 · Multimodal Module (2 hrs, 11 mins)
Learn how to build real applications with the Model Context Protocol (MCP), from first principles to advanced integrations. In this course, you will start by understanding the core MCP architecture and building your first server with Python and FastMCP. You will then add Tools, Resources, and Prompts, inspect them with MCP Inspector, and move on to building custom MCP clients that can work programmatically with LLMs through the Anthropic API. From there, you will explore advanced features such as Elicitation for human-in-the-loop workflows, Roots for filesystem security, and Sampling for client-side AI execution. Finally, you will bring everything together by building a full-stack ChatGPT App that serves a React frontend from a Python MCP backend using the OpenAI Apps SDK. By the end of the course, you will understand how MCP hosts, clients, and servers fit together, how to design reliable tool schemas and resources, and how to ship MCP-powered experiences that work in desktop clients, custom programs, and ChatGPT.
Go to module
Expand module content Hide module content Show module content Hide module content