Learn Agentic AI - From Basics to Advanced Multi-Agent Systems

Master the fundamentals and advanced concepts of Agentic AI through this comprehensive 11-hour 32-minute course covering autonomous intelligent AI agents using Large Language Models and modern AI frameworks. Explore the limitations of traditional AI and discover how Generative AI and Agentic AI work together to create powerful solutions. Learn about different types of AI agents including reactive, utility-based, goal-based, and LLM agents through detailed explanations and practical examples. Build hands-on projects starting with simple reflex agents in Python, progressing to smart room cleaning agents, and advancing to complex multi-agent systems. Gain expertise in essential frameworks including LangChain, LangGraph, CrewAI, and Agno (formerly Phidata) for building sophisticated AI workflows. Understand reinforcement learning basics, Q-learning algorithms, and value functions with Bellman equations to create learning agents. Implement real-world applications such as chatbots, planners, and trading bots while mastering prompt engineering and tool integration techniques. Explore cutting-edge topics including Model Context Protocol (MCP), custom MCP server creation, Agentic RAG systems, and OpenAI Agents SDK integration. Practice building and deploying AI agents both locally and on cloud platforms with step-by-step tutorials and GitHub resources provided for each lesson.

Syllabus

L-1 | Why Traditional AI Fails: Key Limitations Explained
L-2 | What is Agentic AI?
L-3 | What is Generative AI?
L-4 | How Generative AI and Agentic AI can be used together
L-5 | What are AI Agents
L-6 | What are LLM Agents
L-7 | Types of AI Agents | Explained with examples
L-8 Build a Simple Reflex Agent in Python | Create a Smart Room Cleaning Agent
L-9 Goal-Based Agents Using Langchain Streamlit | Agentic AI
L-10 Learning Agents | Agentic AI Course
L-11 Reinforcement Learning Basics | Agentic AI Course
L-12 Value Function in Reinforcement Learning | V(s) Explained with Bellman Equation & Example
L-13 Learning Agents | Q-Learning Explained | Reinforcement Learning Tutorial with Python
L-14 LangGraph Tutorial: Build Agentic AI Systems Step by Step | Agentic AI
L-15 CrewAI - Agentic AI Framework
L-16 | Understanding Agno (formerly Phidata) : Multimodal Agentic AI Framework
L-17 Agno Tutorial: Create AI Agents with Tools & Memory
L-18 Agentic RAG with Agno
L-19 What is MCP (Model Context Protocol)?
L-20 How to Run and Connect Multiple MCP Servers with LangGraph on Local Machine
L-21 Creating a Custom MCP Server with LangGraph & Streamlit | Step by Step tutorial
L-22 Build a custom MCP server on the cloud from scratch | Step by Step tutorial
L-23 Using MCP Servers with Agno: From Local Setup to Cloud Deployment
L-24 How to Build Agentic AI Apps with OpenAI Agents SDK
L-25 How to Use MCP with OpenAI Agents SDK