دانلود کتاب راهنمای مصور برای عامل‌های هوش مصنوعی: ساخت سیستم‌های خودمختار با LLMها، ابزارها و حافظه

Something remarkable happened in the years following the broad public usage of large language models (LLMs): they stopped just talking and started doing. Given a goal, a set of tools, and a bit of memory, an LLM can now search the web, write and run code, revise its own plans, and work through problems over many steps with little hand-holding. We call these systems AI agents, and they represent one of the most consequential shifts in how work gets done and how software gets built. This book provides a comprehensive and highly visual introduction to the world of AI agents, covering both the conceptual foundations and practical applications. We start with the “brain” of today’s most powerful agents, the reasoning LLM, and then build the agent up piece by piece: memory, tools, planning, and reflection. From there we look at how agents behave as systems, how to evaluate them, and how they specialize, whether that means multiple agents collaborating, agents that can see and hear, or the coding agents that have become a staple of modern software development. The main goal of this book is to build intuition. The pace of development in AI agents is even more dizzying than that of the LLMs that power them. New frameworks, protocols, and architectures appear weekly, and keeping up can feel like a losing battle. Instead of chasing the latest releases, we focus on the fundamentals of agents, the components and principles that remain strikingly consistent underneath the churn, so that whatever comes next, you will have the mental models to understand it. To achieve this, we return to the intuition-first philosophy of our previous book, Hands-On Large Language Models. The response to that book, from readers across industries, backgrounds, and languages, convinced us that visual, intuition-driven explanations are not a simplification of technical material but often the most direct path into it. So once again, we use visual language liberally. Hundreds of original illustrations give a visual identity to the major concepts and processes of agentic systems. One figure in particular, introduced in Chapter 1, serves as the foundation of the entire book. It shows the anatomy of an agent, and every subsequent chapter zooms into one of its components, so that by the end you will have assembled the complete picture piece by piece. This book is about agents backed by LLMs. Other kinds of AI agents exist in practice, but rather than writing “LLM-backed AI agents” at every mention, we simply say AI agents and trust you to recall which kind we mean. One more thing before we begin. The figures in this book are all custom made, and each went through more rounds of sketching, argument, and redrawing than we care to count before it earned its page. We worked this way because we were not assembling information for sale; we were making something for you, as carefully as we knew how. What we hope you do with it is a question we have saved for the afterword, on the very last page.