Build an AI Agent (from Scratch): Agents That Reason, Plan, and ACT Autonomously (Paperback)
暫譯: 從零開始建立 AI 代理:能夠推理、計畫並自主行動的代理
Hur, Jungjun, Song, Younghee
買這商品的人也買了...
-
jQuery 實戰手冊 (jQuery in Action, 2/e)$520$410 -
Arduino 官方正版 Genuino 101$1,700$1,700 -
破解線上遊戲:電玩駭客的自動化 Bot 開發寶典 (Game Hacking: Developing Autonomous Bots for Online Games)$550$429 -
Soft Skills 軟實力|軟體開發人員的生存手冊 (Soft Skills: The software developer's life manual)$520$410 -
Raspberry Pi 3 Model B+ (UK製)$1,720$1,685 -
測試用一元商品$0$1 -
領域驅動設計:軟體核心複雜度的解決方法 (Domain-Driven Design: Tackling Complexity in the Heart of Software)$680$578 -
$1,320Deep Learning with JavaScript: Neural Networks in Tensorflow.Js -
機器學習的數學基礎 : AI、深度學習打底必讀$580$458 -
軟體開發人員職涯發展成功手冊 (The Complete Software Developer's Career Guide: How to Learn Programming Languages Quickly, Ace Your Programming Interview, and Land Your Software Developer Dream Job)$880$695 -
Kent Beck 的測試驅動開發:案例導向的逐步解決之道 (Test-Driven Development: By Example)(TDD)$560$436 -
深度強化式學習 (Deep Reinforcement Learning in Action)$1,000$790 -
Reinforcement Learning|強化學習深度解析 (繁體中文版) (Reinforcement Learning: An Introduction, 2/e)$1,200$948 -
Keras 大神歸位:深度學習全面進化!用 Python 實作 CNN、RNN、GRU、LSTM、GAN、VAE、Transformer$1,200$948 -
AI Agents in Action (Paperback)$2,330$2,213 -
$408AI全能助手 人人都能玩轉DeepSeek -
$580數據治理 概念方法與實踐 -
LLM Design Patterns: A Practical Guide to Building Robust and Efficient AI Systems (Paperback)$2,050$1,947 -
軟體測試修練指南:我獨自升級的實戰心法(iThome鐵人賽系列書)$690$538 -
$425基於RISC-V架構的OpenHarmony應用開發與實踐 -
LlamaIndex 大模型 RAG 開發實踐$834$792 -
混合雲安全架構|零信任原則的安全設計方法與實作 (Security Architecture for Hybrid Cloud: A Practical Method for Designing Security Using Zero Trust Principles)$780$616 -
Kafka for Architects: Event-Driven Architecture, Logs, Microservices, Real-Time Event Processing (Paperback)$2,820$2,679 -
軟體開發身分安全實務|開發人員必須掌握的最佳做法 (Identity Security for Software Development: Best Practices That Every Developer Must Know)$620$489 -
$2,592Agentic Graphrag: Integrating Knowledge Graphs, Reasoning, and Agency for Enterprise AI (Paperback)
相關主題
商品描述
Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.
LLM-powered AI agents are the next leap in applied AI, capable of reasoning and collaboration to achieve even complex, multi-step goals. Using new protocols like MCP and A2A, agents can use software tools, retrieve relevant knowledge, and adapt to feedback. This book guides you step by step in creating an AI agent from the ground up, with clear, detailed explanations you can follow to build your own custom assistants!
In this book, bestselling author Jungjun Hur and AI expert Younghee Song guide you through creating a complete research assistant agent framework. You'll learn how agents function under the hood--all without hidden abstractions, black boxes, or framework lock-in. You will implement each piece as you develop a mental model of how agents really work.
In Build an AI Agent (From Scratch) you will learn how to:
- Implement a ReAct (Thought → Action → Observation) loop
- Use MCP to integrate tools calls into your agent's workflow
- Agentic RAG for relevant responses
- Create memory modules that store facts, context, and evolving goals
- Enable agents to plan, reflect, and self-correct
- Build specialized agents, including a code execution agent
- Design multi-agent systems
About the book
Build an AI Agent (From Scratch) is a step-by-step guide to creating a working AI agent, starting with the bare essentials and growing your AI into a full-featured, real-world system. You will connect your agent to powerful software tools, implement a reasoning loop, and then extend your agent with retrieval, memory, planning, reflection, and even multi-agent coordination. Along the way, you will work through production-grade code snippets, full prompts and configs, and "make it better" exercises that encourage you to extend and improve your system. By the final chapter, you will have built an end-to-end AI agent that you can use as a foundation for your own projects.
About the reader
For Python developers and AI practitioners. All examples run on a standard laptop.
About the author
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.
購買印刷書籍時,您將獲得Manning提供的免費電子書(PDF或ePub),以及在線liveBook格式的訪問權限(及其AI助手,能以任何語言回答您的問題)。
LLM驅動的AI代理是應用AI的下一個飛躍,能夠進行推理和協作,以實現複雜的多步驟目標。使用像MCP和A2A這樣的新協議,代理可以使用軟體工具、檢索相關知識並適應反饋。本書逐步指導您從零開始創建AI代理,提供清晰、詳細的解釋,讓您能夠構建自己的自定義助手!
在本書中,暢銷書作者Jungjun Hur和AI專家Younghee Song將指導您創建完整的研究助手代理框架。您將學習代理在背後如何運作——所有這些都不涉及隱藏的抽象、黑箱或框架鎖定。您將在發展對代理實際運作的心理模型的同時實現每一個部分。
在從零開始構建AI代理中,您將學習如何:
- 實現ReAct(思考 → 行動 → 觀察)循環
- 使用MCP將工具調用整合到您的代理工作流程中
- 使用Agentic RAG獲得相關回應
- 創建存儲事實、上下文和不斷演變目標的記憶模塊
- 使代理能夠計劃、反思和自我修正
- 構建專門的代理,包括代碼執行代理
- 設計多代理系統
關於本書
從零開始構建AI代理是一本逐步指南,教您如何創建一個可運作的AI代理,從基本要素開始,將您的AI發展成一個功能齊全的現實系統。您將把代理連接到強大的軟體工具,實現推理循環,然後通過檢索、記憶、計劃、反思,甚至多代理協調來擴展您的代理。在此過程中,您將處理生產級的代碼片段、完整的提示和配置,以及鼓勵您擴展和改進系統的“改進它”練習。到最後一章時,您將構建一個端到端的AI代理,您可以將其用作自己項目的基礎。
關於讀者
適合Python開發者和AI從業者。所有示例均可在標準筆記本電腦上運行。
關於作者
Jungjun Hur是一名AI和數據工程師,擁有電子商務和AI行業的經驗,曾構建生產就緒的AI應用程序和LLM驅動的功能。他是暢銷書《使用LLMs的實用AI應用開發》的作者。
Younghee Song是PwC的AI顧問。她畢業於漢陽大學,獲得經濟學和金融學位,並持有首爾國立大學的人因工程碩士學位。
以上中文內容由 AI 翻譯作者簡介
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.
洪正俊是一位擁有電子商務和人工智慧產業經驗的人工智慧與數據工程師,他曾構建生產就緒的人工智慧應用程式和基於大型語言模型(LLM)的功能。他是暢銷書《使用LLM的實用人工智慧應用開發》的作者。
宋英姬是PwC的人工智慧顧問。她畢業於漢陽大學,獲得經濟學和金融學學位,並持有首爾國立大學的人因工程碩士學位。
以上中文內容由 AI 翻譯