Course Overview
How do AI agents collaborate, connect to data, and scale to handle complex workflows? Ever wondered how multiple AI agents can work together — sharing data, tools, and decisions to get complex jobs done? This course introduces the building blocks behind collaborative AI systems in a simple, practical way. You’ll start with a quick refresher on creating a single agent, then learn how agents connect to external information using Retrieval-Augmented Generation (RAG) — a method that helps them stay accurate and up-to-date based on a connected knowledge base. Next, you’ll explore the Model Context Protocol (MCP), an emerging standard that enables safe, consistent communication between agents, APIs, and real-world tools. Through guided examples, you’ll begin with simple agent workflows — such as sequential and branching flows — to see how agents coordinate basic decisions and actions. From there, you’ll explore more advanced collaboration patterns like the Orchestrator–Worker models, which demonstrate how agents can divide tasks, share progress, and refine results through feedback and reflection. The course also encourages experimentation with other emerging architectures introduced during class discussions and labs. By the end of this course, you’ll understand how AI agents can work together as a team — accessing the right data, coordinating their actions, and learning from experience. All activities use clear, instructor-guided labs in Google Colab and GitHub, with workflows built using LangGraph, LangChain, n8n, and other emerging tools. A basic familiarity with Python or any programming language is helpful. Please note that this course is offered by NAIT in partnership with a third party. Accordingly, this outline originates from a third party.