Foundations of Agentic AI: Llms, Reasoning, Agents, and Applications

This book introduces the fundamentals, architectures, and applications of Agentic AI. It covers intelligent agents, agent types, BDI architecture, and the PEAS framework. It explains LLMs, Transformers, prompt engineering, reasoning, embeddings, and context management. The book explores agent components such as planning, memory, decision making, tool calling, APIs, and RAG. It introduces popular frameworks including LangChain, LangGraph, CrewAI, AutoGen, and Spring AI. Multi-agent systems and their collaboration and communication are discussed with applications in healthcare, education, finance, and manufacturing. The book also covers coding, research, and customer-support agents. Finally, it addresses evaluation, safety, security, privacy, explainability, deployment, governance, ethics, and the future of Agentic AI.