Agentic AI

Introduction to Agentic AI

Understanding the paradigm shift from passive chatbots to active agents. We define what makes an AI 'agentic': the ability to perceive, reason, plan, and act autonomously to achieve goals. We explore the core architecture of modern agents.

Core Components: Memory & Planning

Deep dive into the cognitive architecture of agents. Learn how to implement short-term and long-term memory (Vector DBs) and explore planning strategies like ReAct (Reasoning + Acting) and Chain of Thought to enable complex problem-solving.

Tool Use & Function Calling

Agents are only as powerful as the tools they wield. Master the art of defining tools and function schemas that allow LLMs to interact with the real world—APIs, databases, and software systems. We will build a custom toolset for a live agent.

Multi-Agent Frameworks

Introduction to multi-agent orchestration. Learn how to design systems where specialized agents (e.g., a Researcher, a Writer, and a Reviewer) collaborate to solve complex tasks. We will use frameworks like LangGraph or AutoGen.

Model Context Protocol (MCP)

Explore the new standard for connecting AI models to data and tools. Understand how MCP simplifies the integration of agents with local and remote resources, and build a simple MCP server.

Capstone Project: Autonomous Workflow

Apply everything you've learned to build a fully autonomous workflow. Participants will design and implement an agentic system that solves a specific business problem, from trigger to final output, demonstrating real-world value.