This resource provides a structured overview of Agentic AI—where large language models evolve from passive responders to autonomous, goal-driven agents. Learners will explore how to build, orchestrate, and deploy AI agents capable of using tools, memory, and decision logic to complete tasks across domains. Designed for developers, researchers, and product teams, this module covers key building blocks of modern agentic systems, including multi-agent workflows, vector-based memory, tool calling, and autonomous decision loops. 📘 Topics Covered: Foundations of Agentic AI vs traditional LLMs ReAct, LangGraph, and CrewAI frameworks Designing agent architectures: memory, planning, and tool use Integration with vector stores (e.g. Pinecone, ChromaDB) Use cases: customer support agents, research copilots, automation bots Best practices for prompt engineering, tool orchestration, and cost control