{"product_id":"build-an-ai-agent-from-scratch-9781633434615","title":"Build an AI Agent (From Scratch)","description":"\u003cp\u003e\u003cstrong\u003eBuild an AI Agent (From Scratch): Agents that reason, plan, and act autonomously\u003c\/strong\u003e by \u003cstrong\u003eJungjun Hur and Younghee Song\u003c\/strong\u003e is a practical, step-by-step guide to \u003cstrong\u003eAI agent development, LLM agents, Agentic AI, and autonomous AI systems\u003c\/strong\u003e. The book teaches Python developers and AI practitioners how to build a sophisticated AI agent from the ground up while understanding what happens inside modern agentic systems.\u003cspan class=\"PDq2pG_selectionAnchor\"\u003e\u003c\/span\u003e\u003c\/p\u003e\u003cp\u003eInstead of relying entirely on black-box AI agent frameworks, this book takes you through the underlying mechanics of building an \u003cstrong\u003eAI agent from scratch\u003c\/strong\u003e. You will learn how LLMs can reason about complex tasks, select and use tools, retrieve information, maintain memory, plan actions, reflect on results, and work with other specialized agents.\u003c\/p\u003e\u003cp\u003eStarting with the fundamentals of \u003cstrong\u003eLLM-powered AI agents\u003c\/strong\u003e, you will learn how to distinguish traditional developer-defined workflows from LLM-directed agent loops. The book introduces important concepts such as \u003cstrong\u003eagent loops, structured outputs, Pydantic, tool calling, context engineering, reasoning, planning and evaluation\u003c\/strong\u003e.\u003c\/p\u003e\u003cp\u003eYou will then build your agent's capabilities step by step using \u003cstrong\u003ePython\u003c\/strong\u003e, including web search, local file exploration, vector-based \u003cstrong\u003eRAG (Retrieval-Augmented Generation)\u003c\/strong\u003e and long-term memory. The book also explores \u003cstrong\u003eAgentic RAG\u003c\/strong\u003e, allowing AI agents to retrieve and use relevant information while solving complex, multi-step problems.\u003c\/p\u003e\u003cp\u003eA major focus is on \u003cstrong\u003econtext engineering\u003c\/strong\u003e, helping you understand how to structure information effectively and reduce problems such as context rot and the \"Lost in the Middle\" effect. You will also learn how AI agents can remember previous failures, maintain state and adapt their behaviour over time.\u003c\/p\u003e\u003cp\u003eThe book introduces the \u003cstrong\u003eModel Context Protocol (MCP)\u003c\/strong\u003e for connecting AI agents with external tools and servers. You will learn how tool calling and external integrations can extend the capabilities of an LLM agent beyond simple text generation.\u003c\/p\u003e\u003cp\u003eAs your AI agent becomes more sophisticated, you will explore \u003cstrong\u003eplanning, procedural reflection and self-correction\u003c\/strong\u003e to help prevent hallucinations and endless agent loops. The book also introduces the \u003cstrong\u003eCode-Act paradigm\u003c\/strong\u003e, allowing an agent to securely write and execute code in sandboxed environments.\u003c\/p\u003e\u003cp\u003eThe final stages explore \u003cstrong\u003emulti-agent systems and agent orchestration\u003c\/strong\u003e. You will learn how specialized AI agents can collaborate through the \u003cstrong\u003eA2A protocol\u003c\/strong\u003e, with tasks distributed among multiple agents to improve efficiency and solve complex problems.\u003c\/p\u003e\u003cp\u003eThe book also covers \u003cstrong\u003eAI agent observability and evaluation\u003c\/strong\u003e, including LLM-as-a-judge approaches and OpenTelemetry-based tracing. This provides practical insight into monitoring, evaluating and improving AI agent performance.\u003c\/p\u003e\u003cp\u003eBy building the complete system from the ground up, \u003cstrong\u003eBuild an AI Agent (From Scratch)\u003c\/strong\u003e provides a practical foundation for anyone who wants to understand and develop modern \u003cstrong\u003eAI agents, autonomous agents, LLM applications and multi-agent systems\u003c\/strong\u003e.\u003c\/p\u003e\u003ch3\u003eWhat You Will Learn\u003c\/h3\u003e\u003cul\u003e\n\u003cli\u003eBuild an autonomous \u003cstrong\u003eAI agent from scratch using Python\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eUnderstand how \u003cstrong\u003eLLM agents\u003c\/strong\u003e reason, act and make decisions\u003c\/li\u003e\n\u003cli\u003eImplement \u003cstrong\u003eReAct (Reasoning\/Action) agent loops\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eUse dynamic \u003cstrong\u003eAI tool calling\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eApply structured outputs with \u003cstrong\u003ePydantic\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eUnderstand and apply \u003cstrong\u003econtext engineering\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eBuild \u003cstrong\u003eAgentic RAG\u003c\/strong\u003e and vector-based retrieval\u003c\/li\u003e\n\u003cli\u003eImplement \u003cstrong\u003eAI agent memory and state persistence\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eAdd web search and external tools to AI agents\u003c\/li\u003e\n\u003cli\u003eUse \u003cstrong\u003eMCP (Model Context Protocol)\u003c\/strong\u003e with AI agents\u003c\/li\u003e\n\u003cli\u003eImplement planning, reflection and self-correction\u003c\/li\u003e\n\u003cli\u003eBuild sandboxed \u003cstrong\u003eAI code execution\u003c\/strong\u003e systems\u003c\/li\u003e\n\u003cli\u003eDesign and orchestrate \u003cstrong\u003emulti-agent systems\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eExplore the \u003cstrong\u003eA2A protocol\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003eImplement AI agent observability and evaluation\u003c\/li\u003e\n\u003cli\u003eUse \u003cstrong\u003eLLM-as-a-judge\u003c\/strong\u003e evaluation techniques\u003c\/li\u003e\n\u003cli\u003eTrace and improve AI agent performance with OpenTelemetry\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003e\u003cb\u003eWhat's inside\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003e• End-to-end construction of a framework-free, autonomous AI agent in Python\u003cbr\u003e• Advanced practical integrations including MCP, vector-based RAG, long-term memory, and sandboxed code execution\u003cbr\u003e• Multi-agent orchestration and automated LLM-as-a-judge evaluation pipelines\u003c\/p\u003e\u003cp\u003e\u003cspan style=\"color: rgb(34, 34, 34); font-size: 24px; font-weight: 700;\"\u003eWho This Book Is For\u003c\/span\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003eThis book is aimed at \u003cstrong\u003ePython developers, AI developers, machine learning practitioners and AI engineers\u003c\/strong\u003e who want to understand how AI agents work internally and learn how to build agentic systems without depending completely on abstract frameworks.\u003c\/p\u003e\u003cp\u003eIf you want to learn \u003cstrong\u003eAI agent development, LLM agents, Agentic AI, autonomous AI systems, RAG, MCP, AI memory, tool calling or multi-agent architectures\u003c\/strong\u003e, this book provides a hands-on approach to building these technologies from first principles.\u003c\/p\u003e\u003cp\u003eThe publisher confirms that the book focuses on building a working AI agent step by step, including ReAct loops, MCP, Agentic RAG, memory, planning, specialized agents and multi-agent systems\u003c\/p\u003e\u003cp\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003ePart 1\u003cbr\u003e1 What is an AI agent?\u003cbr\u003e2 The brain of AI agents: LLMs\u003cbr\u003e3 Enabling actions: Tool use\u003cbr\u003e4 Implementing a basic ReAct agent\u003cbr\u003ePart 2\u003cbr\u003e5 Building knowledge bases with RAG\u003cbr\u003e6 Adding memory to your agent\u003cbr\u003e7 Planning and reflection for complex tasks\u003cbr\u003e8 Empowering agents with code execution\u003cbr\u003e9 Orchestrating multi-agent systems\u003cbr\u003e10 Evaluating agents\u003cbr\u003eA OpenAI API Key\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eEbook License\u003c\/strong\u003e\u003c\/p\u003e\u003cp\u003eEnd-User Warranty And License Agreement\u003c\/p\u003e\u003cp\u003e1. Grant Of License\u003c\/p\u003e\u003cp\u003eManning Has Authorized The Download By You Of An Unrestricted Number Of Copies Of The Electronic Book (Ebook) In Any Of The Available Formats. Manning Grants You A Nonexclusive, Nontransferable License To Use The Ebook According To The Terms And Conditions Herein. This License Agreement Permits You To Install The Ebook On Any And All Your Devices For Your Personal Use Only.\u003c\/p\u003e\u003cp\u003e2. Restrictions\u003c\/p\u003e\u003cp\u003eYou Shall Not: (1) Share, Resell, Rent, Assign, Timeshare, Distribute, Or Transfer All Or Part Of The Ebook Or Any Rights Granted Hereunder To Any Other Person; (2) Duplicate The Ebook, Except For A Single Backup Or Archival Copy; (3) Remove Any Proprietary Notices, Labels, Or Marks From The Ebook; (4) Transfer Or Sublicense Title To The Ebook To Any Other Party.\u003c\/p\u003e\u003cp\u003e3. Intellectual Property Protection\u003c\/p\u003e\u003cp\u003eThe Ebook Is Owned By Manning And Is Protected By United States And International Copyright And Other Intellectual Property Laws. Manning Reserves All Rights In The Ebook Not Expressly Granted Herein. This License And Your Right To Use The Ebook Terminate Automatically If You Violate Any Part Of This Agreement. In The Event Of Termination, You Must Remove The Original And Any Copies Of The Ebook From All Your Devices.\u003c\/p\u003e\u003cp\u003e4. Source Code Supplementary Material\u003c\/p\u003e\u003cp\u003eAny Source Code Files Provided As A Supplement To The Book Are Freely Available To The Public For Download. Reuse Of The Code Is Permitted, In Whole Or In Part, Including The Creation Of Derivative Works, Provided That You Acknowledge That You Are Using It And Identify The Source: Title, Publisher And Year.\u003c\/p\u003e\u003cp\u003e5. Limited Warranty\u003c\/p\u003e\u003cp\u003eManning Warrants That The Ebook Files, A Copy Of Which You Are Authorized To Download, Are Free From Defects In The Operational Sense That They Can Be Read By A Pdf Reader Or Epub Reader, Or Other. Except For This Express Limited Warranty, Manning Makes And You Receive No Warranties, Express, Implied, Statutory Or In Any Communication With You, And Manning Specifically Disclaims Any Other Warranty Including The Implied Warranty Of Merchantability Or Fitness Or A Particular Purpose. Manning Does Not Warrant That The Operation Of The Ebook Will Be Uninterrupted Or Error Free. If The Ebook Was Purchased In The United States, The Above Exclusions May Not Apply To You As Some States Do Not Allow The Exclusion Of Implied Warranties. In Addition To The Above Warranty Rights, You May Also Have Other Rights That Vary From State To State.\u003c\/p\u003e\u003cp\u003e6. Limitation Of Liability\u003c\/p\u003e\u003cp\u003eIn No Event Will Manning Be Liable For Any Damages, Whether Arising For Tort Or Contract, Including Loss Of Data, Lost Profits, Or Other Special, Incidental, Consequential, Or Indirect Damages Arising Out Of The Use Or Inability To Use The Ebook.\u003c\/p\u003e\u003cp\u003e7. General\u003c\/p\u003e\u003cp\u003eThis Agreement Constitutes The Entire Agreement Between You And Manning And Supersedes Any Prior Agreement Concerning The Ebook. This Agreement Is Governed By The Laws Of The State Of New Yor\u003c\/p\u003e\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e","brand":"Manning Publications","offers":[{"title":"Paperback","offer_id":50506763829318,"sku":"9781633434615","price":5318.0,"currency_code":"INR","in_stock":true},{"title":"E-Book","offer_id":50506763862086,"sku":"9781633434615-2","price":3782.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/2797\/1142\/files\/71-l_FlNFGL._SL1500.jpg?v=1790332643","url":"https:\/\/cb-india.com\/products\/build-an-ai-agent-from-scratch-9781633434615","provider":"Computer Bookshop (India) Pvt Ltd","version":"1.0","type":"link"}