Agentic AI, RAG, LangGraph, and MCP with Python: Building Autonomous Intelligent Systems
1 enrolled
30 lessons
What you'll learn
- Introduction to Agentic AI and Course Overview
- Python Foundations for AI: Data Structures and Libraries
- Exploring LLM APIs and Local Models with Python
- Fundamentals of Prompt Engineering and Context Design
- Understanding Vector Databases and Embeddings
- Introduction to Retrieval-Augmented Generation (RAG)
- Building Retrieval Pipelines with Python
- Tool Calling and Integration for Enhanced AI Workflows
- Getting Started with LangChain: Architecture and Setup
- Deep Dive into LangGraph for Visualizing AI Agents
+ 20 more topics
About this course
This intermediate Python course guides learners through the foundations of AI programming focusing on Retrieval-Augmented Generation (RAG), LangGraph workflows, and the Model Context Protocol (MCP). Explore Python for AI, LLM APIs, prompt engineering, vector databases, multi-agent setups, security, and cloud deployment. Engage with supportive graphics and gamified exercises to build an autonomous research and business automation platform as your capstone project.
Curriculum
- 1 Introduction to Agentic AI and Course Overview Quiz
- 2 Python Foundations for AI: Data Structures and Libraries Quiz
- 3 Exploring LLM APIs and Local Models with Python
- 4 Fundamentals of Prompt Engineering and Context Design Quiz
- 5 Understanding Vector Databases and Embeddings
- 6 Introduction to Retrieval-Augmented Generation (RAG)
- 7 Building Retrieval Pipelines with Python
- 8 Tool Calling and Integration for Enhanced AI Workflows
- 9 Getting Started with LangChain: Architecture and Setup
- 10 Deep Dive into LangGraph for Visualizing AI Agents
- 11 Implementing the Model Context Protocol (MCP) Fundamentals
- 12 Multi-Agent Workflows: Coordination and Communication
- 13 Memory Management Strategies in Agentic AI Systems
- 14 Human Approval Loops: Incorporating Feedback Effectively
- 15 Evaluation Metrics for Agentic AI Performance
- 16 Security Best Practices in AI Applications
- 17 Monitoring and Logging AI Agent Activities
- 18 Optimizing AI Workflows for Scalability
- 19 Deploying AI Systems to the Cloud with Python
- 20 Integrating LangChain and LangGraph for Complex Tasks
- 21 Advancing RAG Techniques: Hybrid and Dynamic Retrieval
- 22 Designing Agentic AI with MCP for Real-World Use Cases
- 23 Debugging and Troubleshooting Multi-Agent Systems
- 24 Incorporating Gamification to Enhance AI Interaction
- 25 Visualization Tools for AI Workflow Monitoring
- 26 Ethical Considerations and Bias Mitigation
- 27 Performance Tuning for LLM APIs and Local Models
- 28 Securing Data and Models in AI Deployments
- 29 Automation Strategies for Business and Research Tasks
- 30 Capstone Project Introduction: Autonomous Research & Business Platform