防詐3要訣：不聽信、不操作、掛斷電話 
Build an AI Agent (from Scratch): Agents That Reason, Plan, and ACT Autonomously
BUILD AN AI AGENT (FROM SCRATC
出版社：
出版日期：
2026/08/17
2,700
訂單自國外空運，約14-21個工作天(不含例假日)到貨後依序出貨。為縮短等待，建議將此商品和其他商品分開下單。
查詢門市庫存
內容簡介
Get the eBook free when you register your print book at Manning.
"A practical guide for anyone who wants to move beyond demos and create agentic systems with confidence."
--Elliot Kim, Coupang Inc. This book is a fascinating step-by-step journey through design, development, and deployment of a system of autonomous AI agents. Authors Jungjun Hur and Younghee Song guide you concept-by-concept as you build a sophisticated research agent in Python, designed to solve complex, multi-step tasks from the rigorous GAIA (General AI Assistants) benchmark. By seeing the construction of the system end to end, you'll understand how the underlying mechanics unobstructed by any existing blackbox libraries and frameworks. This book includes ten meaty chapters and a handy appendix (about how to get an OpenAI API key). The technical explanations throughout the book are made crystal clear by the use of many helpful diagrams. As one reviewer remarked, even for someone building their first agent, "nothing feels like magic or a mystery after the first few chapters!" Early on, you'll establish the foundational blueprint for your agent by distinguishing rigid developer-defined workflows from true, LLM-directed agent loops. You'll learn how to manage stateless APIs, enforce structured outputs using Pydantic, and implement dynamic tool-calling. Crucially, the book centers on "Context Engineering"--the discipline of systematically structuring information to prevent context rot and the "Lost in the Middle" effect. One technical reviewer particularly appreciated that core concepts like agent loops, context engineering, and evaluation are introduced with clear motivation and practical examples rather than as isolated abstractions. After you build the basic agent, you'll progressively expand its capabilities by integrating custom web search, local file system exploration, and vector-based RAG to navigate complex data. You'll also enable the agent to recall past failures and adapt state persistence through hierarchical context optimization and longterm memory. Along the way, you'll see how to use the Model Context Protocol (MCP) to seamlessly connect your agent to external tools and servers. Later chapters push into advanced territory. To prevent the agent from hallucinating or looping during complex tasks, you'll implement explicit planning and procedural reflection. Then, you'll explore the Code-Act paradigm, empowering the agent with sandboxed cloud environments to securely write scripts, run CLI commands, and compose tools dynamically. Finally, you'll up-scale your project from a single agent into a collaborative, multi-agent architecture using the A2A protocol, where specialized tasks are routed to isolated sub-agents to maximize token efficiency. Because highly autonomous agents carry real-world risks, the book culminates in a rigorous observability and evaluation pipeline. You'll implement an automated LLM-as-a-judge system--powered by Open Telemetry--to trace, grade, and continuously refine the agent's trajectory and outputs. By building every layer from the ground up, the book ensures that readers are left with a deep, practical understanding of AI mechanics. What's inside - End-to-end construction of a framework-free, autonomous AI agent in Python
- Advanced practical integrations including MCP, vector-based RAG, long-term memory, and sandboxed code execution
- Multi-agent orchestration and automated LLM-as-a-judge evaluation pipelines About the reader For Python developers with some knowledge of machine learning who want to build and deeply understand agentic systems without relying on abstract libraries. About the author Jungjun Hur is an independent AI and data engineer who specializes in building agentic systems for e-commerce. He is the author of Practical AI Application Development Using LLMs. Younghee Song is an AI consultant at PricewaterhouseCoopers (PwC). Both authors live and work in South Korea. Table of Contents Part 1
1 What is an AI agent?
2 The brain of AI agents: LLMs
3 Enabling actions: Tool use
4 Implementing a basic ReAct agent
Part 2
5 Building knowledge bases with RAG
6 Adding memory to your agent
7 Planning and reflection for complex tasks
8 Empowering agents with code execution
9 Orchestrating multi-agent systems
10 Evaluating agents
A OpenAI API Key
--Elliot Kim, Coupang Inc. This book is a fascinating step-by-step journey through design, development, and deployment of a system of autonomous AI agents. Authors Jungjun Hur and Younghee Song guide you concept-by-concept as you build a sophisticated research agent in Python, designed to solve complex, multi-step tasks from the rigorous GAIA (General AI Assistants) benchmark. By seeing the construction of the system end to end, you'll understand how the underlying mechanics unobstructed by any existing blackbox libraries and frameworks. This book includes ten meaty chapters and a handy appendix (about how to get an OpenAI API key). The technical explanations throughout the book are made crystal clear by the use of many helpful diagrams. As one reviewer remarked, even for someone building their first agent, "nothing feels like magic or a mystery after the first few chapters!" Early on, you'll establish the foundational blueprint for your agent by distinguishing rigid developer-defined workflows from true, LLM-directed agent loops. You'll learn how to manage stateless APIs, enforce structured outputs using Pydantic, and implement dynamic tool-calling. Crucially, the book centers on "Context Engineering"--the discipline of systematically structuring information to prevent context rot and the "Lost in the Middle" effect. One technical reviewer particularly appreciated that core concepts like agent loops, context engineering, and evaluation are introduced with clear motivation and practical examples rather than as isolated abstractions. After you build the basic agent, you'll progressively expand its capabilities by integrating custom web search, local file system exploration, and vector-based RAG to navigate complex data. You'll also enable the agent to recall past failures and adapt state persistence through hierarchical context optimization and longterm memory. Along the way, you'll see how to use the Model Context Protocol (MCP) to seamlessly connect your agent to external tools and servers. Later chapters push into advanced territory. To prevent the agent from hallucinating or looping during complex tasks, you'll implement explicit planning and procedural reflection. Then, you'll explore the Code-Act paradigm, empowering the agent with sandboxed cloud environments to securely write scripts, run CLI commands, and compose tools dynamically. Finally, you'll up-scale your project from a single agent into a collaborative, multi-agent architecture using the A2A protocol, where specialized tasks are routed to isolated sub-agents to maximize token efficiency. Because highly autonomous agents carry real-world risks, the book culminates in a rigorous observability and evaluation pipeline. You'll implement an automated LLM-as-a-judge system--powered by Open Telemetry--to trace, grade, and continuously refine the agent's trajectory and outputs. By building every layer from the ground up, the book ensures that readers are left with a deep, practical understanding of AI mechanics. What's inside - End-to-end construction of a framework-free, autonomous AI agent in Python
- Advanced practical integrations including MCP, vector-based RAG, long-term memory, and sandboxed code execution
- Multi-agent orchestration and automated LLM-as-a-judge evaluation pipelines About the reader For Python developers with some knowledge of machine learning who want to build and deeply understand agentic systems without relying on abstract libraries. About the author Jungjun Hur is an independent AI and data engineer who specializes in building agentic systems for e-commerce. He is the author of Practical AI Application Development Using LLMs. Younghee Song is an AI consultant at PricewaterhouseCoopers (PwC). Both authors live and work in South Korea. Table of Contents Part 1
1 What is an AI agent?
2 The brain of AI agents: LLMs
3 Enabling actions: Tool use
4 Implementing a basic ReAct agent
Part 2
5 Building knowledge bases with RAG
6 Adding memory to your agent
7 Planning and reflection for complex tasks
8 Empowering agents with code execution
9 Orchestrating multi-agent systems
10 Evaluating agents
A OpenAI API Key
作者介紹
Jungjun Hur is an AI and data engineer with experience in e-commerce and AI industries, where he has built production-ready AI applications and LLM-powered features. He is the author of the bestselling book Practical AI Application Development Using LLMs.
Younghee Song is an AI consultant at PwC. She graduated from Hanyang University with a degree in Economics and Finance and holds a Master's in Human Factors Engineering from Seoul National University.
規格
誠品貨碼 /
ISBN13 / 9781633434615
ISBN10 /
EAN貨碼 / 9781633434615
裝訂 / P:平裝
頁數 / 336
重量(g) / 408.2
語言 / 3:英文
級別 / N:無
尺寸 / 23.4X18.5X2.8CM
退貨說明
退貨須知：
- 依照消費者保護法的規定，您享有商品貨到次日起七天猶豫期(含例假日)的權益(請注意！猶豫期非試用期)，辦理退貨之商品必須是全新狀態(不得有刮傷、破損、受潮)且需完整(包含全部商品、配件、原廠內外包裝、贈品及所有附隨文件或資料的完整性等)。
- 請您以送貨廠商使用之包裝紙箱將退貨商品包裝妥當，若原紙箱已遺失，請另使用其他紙箱包覆於商品原廠包裝之外，切勿直接於原廠包裝上黏貼紙張或書寫文字。若原廠包裝損毀將可能被認定為已逾越檢查商品之必要程度，本公司得依毀損程度扣除回復原狀必要費用(整新費)後退費；請您先確認商品正確、外觀可接受，再行拆封，以免影響您的權利；若為產品瑕疵，本公司接受退貨。
依「通訊交易解除權合理例外情事適用準則」，下列商品不適用七日猶豫期，除產品本身有瑕疵外，不接受退貨：
- 易於腐敗、保存期限較短或解約時即將逾期。(如:生鮮蔬果、乳製品、冷凍冷藏食材、蛋糕)
- 依消費者要求所為之客製化給付。(如:客製印章、鋼筆刻字)
- 報紙、期刊或雜誌。
- 經消費者拆封之影音商品或電腦軟體。
- 非以有形媒介提供之數位內容或一經提供即為完成之線上服務，經消費者事先同意始提供。(如:電子書)
- 已拆封之個人衛生用品。(如:內衣褲、襪類、褲襪、刮鬍刀、除毛刀等貼身用品)
- 國際航空客運服務。
若您退貨時有下列情形，可能被認定已逾越檢查商品之必要程度而須負擔為回復原狀必要費用(整新費)，或影響您的退貨權利，請您在拆封前決定是否要退貨：
- 以數位或電磁紀錄形式儲存或著作權相關之商品(包含但不限於CD、VCD、DVD、電腦軟體等) 包裝已拆封者(除運送用之包裝以外)。
- 耗材(包含但不限於墨水匣、碳粉匣、紙張、筆類墨水、清潔劑補充包等)之商品包裝已拆封者(除運送用之包裝以外)。
- 衣飾鞋類/寢具/織品(包含但不限於衣褲、鞋子、襪子、泳裝、床單、被套、填充玩具)或之商品缺件(含購買商品、附件、內外包裝、贈品等)或經剪標或下水或商品有不可回復之髒污或磨損痕跡。
- 食品、美容/保養用品、內衣褲等消耗性或個人衛生用品、商品銷售頁面上特別載明之商品已拆封者(除運送用之包裝外一切包裝、包括但不限於瓶蓋、封口、封膜等接觸商品內容之包裝部分)或已非全新狀態(外觀有刮傷、破損、受潮等)與包裝不完整(缺少商品、附件、原廠外盒、保護袋、配件紙箱、保麗龍、隨貨文件、贈品等)。
- 家電、3C、畫作、電子閱讀器等商品，除商品本身有瑕疵外，退回之商品已拆封(除運送用之包裝外一切包裝、包括但不限於封膜等接觸商品內容之包裝部分、移除封條、拆除吊牌、拆除貼膠或標籤等情形)或已非全新狀態(外觀有刮傷、破損、受潮等)與包裝不完整(缺少商品、附件、原廠外盒、保護袋、配件紙箱、保麗龍、隨貨文件、贈品等)。
- 退貨程序請參閱【客服專區→常見問題→誠品線上退貨退款】之說明。
付款/配送