Build an AI Agent (from Scratch): Agents That Reason, Plan, and ACT Autonomously
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
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.
- 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.
商品描述(中文翻譯)
購買印刷書籍時，您將獲得來自 Manning 的免費電子書（PDF 或 ePub），以及訪問線上 liveBook 格式（及其 AI 助手，能以任何語言回答您的問題）的權限。
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一個 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 將指導您創建一個完整的研究助手代理框架。您將了解代理在背後是如何運作的——所有這些都沒有隱藏的抽象、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 將工具調用整合到代理的工作流程中
- 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組
- 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 針對 Python 開發者和 AI 實踐者。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 LLM 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。
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.
作者簡介(中文翻譯)
許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。他是暢銷書籍使用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。
