Build an AI Agent (From Scratch): Agents that reason, plan, and act autonomously (From Scratch)
by Jungjun Hur and Younghee Song
From $50.99 / copy at 25+ copies; lower per-copy prices at higher quantities (see Volume pricing) As low as $47.99 at 1,000+
Total $1,274.75
Format
The more copies, the less each one costs
Applied automatically in your cart. No code needed.
Turn this order into a program
Groups that order together often pair the copies with something more. We handle the extras so you don't have to.
Branded cover stickers on paperbacks from 100 copies, plus bookplates, inserts and belly bands. Your specialist confirms what fits your title.
Customization options Ship to every readerOne address, many sites or individual recipients' homes, in the US and abroad.
Fulfillment options Pair it with a branded journalJournals with your logo or each reader's name, for the same group.
Branded journalsBookPal is partnering with Talezo to help you find and book authors, speakers and performers for your event.
BookPal × TalezoBuild an AI Agent (From Scratch)
"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
Details
- Publisher
- Manning
- Authors
- Jungjun Hur, Younghee Song
- Format
- Paperback
- Published
- Aug 18, 2026
- ISBN-13
- 9781633434615
- ISBN-10
- 1633434613
- Pages
- 336
Build an AI Agent (From Scratch) for groups: pricing
Volume pricing applies automatically in your cart. No codes, no account needed.
| Copies | Price per copy | You save |
|---|---|---|
| 25 – 99 | $50.99 | 15% off list |
| 100 – 249 | $50.39 | 16% off list |
| 250 – 499 | $49.79 | 17% off list |
| 500 – 999 | $49.19 | 18% off list |
| 1,000+ | $47.99 | 20% off list |
Popular for
A copy for every member, on one order.
A book for every attendee, delivered to your venue.
For clients, staff, members or volunteers.
Where can I buy 100 copies of Build an AI Agent?
BookPal sells Build an AI Agent in quantity. At 100 copies the price is $50.39 a copy, against a list price of $59.99, and the cart applies the volume tier automatically. Free shipping on most orders over $95 in the contiguous US. A specialist can quote a larger or mixed order.
- New books only, straight from the publisher
- Volume prices apply automatically in the cart, with no code needed
- Order at least 10 business days before you need the books (11 from mid-November through December)
What does Build an AI Agent (From Scratch) cost when I buy for a group?
Volume pricing applies automatically in your cart, with no code needed. Price per copy: 25 to 99 copies, $50.99 (15% off list); 100 to 249 copies, $50.39 (16% off list); 250 to 499 copies, $49.79 (17% off list); 500 to 999 copies, $49.19 (18% off list); 1,000+ copies, $47.99 (20% off list). Need a different quantity, or a quote to forward for approval? Ask a specialist and we will confirm pricing before you pay.
How fast can I get copies of Build an AI Agent (From Scratch)?
Need them by a specific date? Request a quote and we'll confirm timing before you pay.
Can you ship to several locations or people's homes?
Yes. We ship group orders to one address, to multiple sites, or to individual recipients, in the US and internationally. See fulfillment options.
Can I get a formal quote for approval before ordering?
Yes. Request a quote and we'll send a PDF you can forward for approval.
Do you accept purchase orders and tax-exempt orders?
Yes. We accept purchase orders upon approval, as well as cards, PayPal, ACH, wire transfers and checks. BookPal is a tax-exempt supplier in all 50 states. See purchase orders and sales tax exemption.
What if I find a lower price?
Send us the link. We match prices from other booksellers and distributors on a new copy in the same edition, available to ship in the quantity you need. Clearance sales and pricing errors are the exception, and we'll tell you quickly if that's the case. Start a price match.
Write a Review
Build an AI Agent (From Scratch): Agents that reason, plan, and act autonomously (From Scratch)
Groups also order




A colleague asked you to approve this order
Your quote list
Add books as you browse, then request one quote for all of them.