This module will cover the essentials of Generative AI as a nice recap or refresher for everyone to be on the same foundational level and then we will dive into the essential concepts and components of both RAG &Agentic AI Systems 

• Whirlwind tour of Generative AI 

• Recap of Prompting LLMs & RAG Systems 

• Introduction to Agentic AI Systems  

• Key components of Agentic AI Systems - LLM, Tools, Memory, Prompts, Routers, Workflows 

• Current tool landscape in Agentic AI  

• Tool Calling or Function Calling - The workhorse of Agentic AI Systems 

• Hands-on: Tool Calling for Agentic AI with LangChain  

• Hands-on: RAG with LangChain & LangGraph 

This module will build on the tool-calling aspects from the previous module and will teach you how to build simple tool-use Agents using LangChain, LangGraph and the ReAct pattern. You will also learn how to add inkey components like guardrails using LangChain's new features like Middleware. 

• Introduction to LangGraph and key components 

• Hands-on: Build a ReAct Tool-Use Agent with LangChain  

• Hands-on: Build a Text2SQL Data Assistant Agent from Scratch using LangGraph 

Design memory-aware agents that work across users and sessions. Learn short-term versus long-term memory, threads and snapshots, and context window management. Use LangMem to persist and retrieve context. Add MCP servers to expose external tools and data. Build a multi-user conversational financial analyst and an adaptive agent that learns from past sessions. 

• Introduction to short-term and long-term memory 

• Threads, memory snapshots, long-term memory stores 

• Managing memory limits and context window limitations 

• Internal and External Memory Stores 

• Hands-on: Build a Conversational Agentic AI Financial Assistant  

• Understanding Model Context Protocol and when you do really need it? 

• Hands-on: Building Agentic AI Systems with Pre built MCP Servers 

• Hands-on: Building Agentic AI Systems with multiple MCP Servers and Clients from Scratch 

• If time permits: How long-term memory is used to build adaptive agents 

This module will focus on how to leverage industry-standard Agentic AI Design patterns and build and architect more advanced Agentic AI Systems leveraging tool-use, planning, reflection and multi-agent systems 

• Key Design Patterns for Architecting Agentic AI Systems - Tool-Use, Planning, Reflection, Multi-Agent System 

• Hands-On: Parallelized Plan Execution in Report Planner Agents 

• Hands-On: Build Multi-Agent Systems for analysis & research - Supervisor / Hierarchical Architectures 

Combine retrieval with agents to route questions to the right data and tools. Learn how to improve your previous RAG system from Module 1 with adaptive RAG, learn about Router Agentic RAG to build a customer support workflow that selects collections, tools, and prompts based on query intent. Jump to multimodal Agentic AI by processing invoices with multimodal LLMs and structured extraction, coordinating multiple agents for parsing, validation, and final summaries. 

• Key Design Patterns for Architecting Agentic RAG Systems - Router RAG, Adaptive RAG, Corrective RAG and more 

• Hands-on: Improving on our previous RAG system with Agentic RAG with LangGraph 

• Hands-On: Build a Router RAG System for Customer Support Resolution 

• Hands-On: Build a Multimodal Multi Agent System for Invoice Processing 

This module will briefly cover the key steps involved in building and deploying a simple Agentic AI System using LangGraph, FastAPI on the cloud and then we cover evaluation and monitoring and tracking the Agent execution briefly using frameworks like LangSmith 

• Key workflow for Building → Deploying → Monitoring an end-to-end Agentic AI System 

• Hands-On: Build a simple LangGraph AI Agent (recap) 

• Hands-On: Wrap AI Agent in a Web Service API using FastAPI 

• Hands-On: Deploy Agentic API in the Cloud (We will deploy via colab itself the same Google Cloud Server where Colab is running) 

• Hands-On: Test & Monitor & Evaluate AI Agent execution and traces 

• Future Scope: Next Steps and Best Practices