Get Discount 10% Off
Subscribe to our newsletters now and stay up-to-date with new arrivals, updates and deals.
MILLIONS OF TITLES TO CHOOSE FROM
Currency
Build an AI Agent (from Scratch): Agents That Reason, Plan, and ACT Autonomously
Get the eBook free when you register your print book at Manning. "A practical guide for anyone...
- $95.98 USD
- $95.98 USD
- Unit price
- per
Please hurry! Only 38 left in stock
Couldn't load pickup availability
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
Author: Jungjun Hur,Younghee Song
Publisher: Manning Publications
Published: 08/18/2026
Pages: 336
Binding Type: Paperback
Weight: 0.90lbs
Size: 9.20h x 7.30w x 1.10d
ISBN: 9781633434615
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.
--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
Author: Jungjun Hur,Younghee Song
Publisher: Manning Publications
Published: 08/18/2026
Pages: 336
Binding Type: Paperback
Weight: 0.90lbs
Size: 9.20h x 7.30w x 1.10d
ISBN: 9781633434615
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.
Returns Policy
You may return most new, unopened items within 30 days of delivery for a full refund. We'll also pay the return shipping costs if the return is a result of our error (you received an incorrect or defective item, etc.).
You should expect to receive your refund within four weeks of giving your package to the return shipper, however, in many cases you will receive a refund more quickly. This time period includes the transit time for us to receive your return from the shipper (5 to 10 business days), the time it takes us to process your return once we receive it (3 to 5 business days), and the time it takes your bank to process our refund request (5 to 10 business days).
If you need to return an item, simply login to your account, view the order using the "Complete Orders" link under the My Account menu and click the Return Item(s) button. We'll notify you via e-mail of your refund once we've received and processed the returned item.
Shipping
We can ship to virtually any address in the world. Note that there are restrictions on some products, and some products cannot be shipped to international destinations.
When you place an order, we will estimate shipping and delivery dates for you based on the availability of your items and the shipping options you choose. Depending on the shipping provider you choose, shipping date estimates may appear on the shipping quotes page.
Please also note that the shipping rates for many items we sell are weight-based. The weight of any such item can be found on its detail page. To reflect the policies of the shipping companies we use, all weights will be rounded up to the next full pound.
- Choosing a selection results in a full page refresh.