Agentic AI: LangChain and LangGraph

This course provides a hands-on introduction to building agentic AI systems with LangChain and LangGraph, teaching you how to create dynamic workflows powered by memory, iteration, reflection, and orchestration. You’ll begin by learning how LangGraph structures agents through nodes and control edges, enabling stateful behavior and complex logic flows. You’ll explore self-improving agent architectures—including Reflection, Reflexion, and ReAct—to design workflows where agents assess their own reasoning, revise earlier steps, and improve output quality. Guided labs help you construct agents that apply feedback loops, refine their reasoning, and enhance performance using structured evaluation techniques. You’ll move into multi-agent design, learning how specialized agents collaborate through orchestration patterns, governance strategies, and clear task routing. You’ll build an agentic RAG system that retrieves context, coordinates multiple reasoning paths, and routes user queries intelligently across agents. By completing this course, you’ll gain the skills to architect robust, adaptive agent systems capable of solving complex tasks through reasoning, collaboration, and retrieval. 39:T1248,

• Explain how agentic frameworks support modular and scalable AI system design
• Apply LangGraph workflow patterns such as sequential flows, routing, and parallelization
• Construct multi-agent applications using CrewAI with tasks, structured outputs, and tool integrations
• Create agents and workflows with BeeAI and design multi-agent conversations using AG2
• Implement orchestration strategies that coordinate multiple agents to solve complex tasks
• Select appropriate frameworks and design patterns to optimize performance and maintainability in AI projects