This book22.9 x 15.2 x 0.5 cm9.02 x 5.98 x 0.2 in
Ship to
Taiwan
Select your location
Shipping costs will be calculated based on this address throughout the site.
Shipping costs will be calculated based on this address throughout the site.
Select your country
Americas
Argentina
Brazil
Canada
Chile
Colombia
Costa Rica
Dominican Republic
Ecuador
El Salvador
Mexico
Peru
U.S.A.
Uruguay
Europe
Austria
Belgium
Croatia
Czech Republic
Denmark
Finland
France
Germany
Greece
Hungary
Ireland
Italy
Latvia
Malta
Netherlands
Norway
Poland
Portugal
Serbia
Slovakia
Slovenia
Spain
Sweden
Switzerland
United Kingdom
Rest of the world
Building AI Agents. A Hands-On Guide to Goal-Driven Agents with Python
Quiet Line Press;Blue J. Lion
Building AI Agents. A Hands-On Guide to Goal-Driven Agents with Python
Quiet Line Press;Blue J. Lion (Author) · Independently published · Paperback
Building AI Agents. A Hands-On Guide to Goal-Driven Agents with Python
Quiet Line Press;Blue J. Lion
Build practical AI agents - without the hype.
AI agents are everywhere in today's tech conversations, but many explanations are vague, overly ambitious, or buried in abstraction.
This book takes a practice-first approach.
You will learn how practical AI agents work by building around a real Python project: a small EXIF privacy agent that reviews image metadata, decides when cleanup may be needed, asks for approval before file changes, and summarizes results in plain language.
Instead of chasing vague autonomy, this guide focuses on the parts that actually matter: goals, planning, tools, safety boundaries, approvals, structured results, and feedback loops.
What you will learnWhat an AI agent is - and what it is notHow agents differ from tools, workflows, chatbots, and MCP serversHow to structure a small goal-driven agent loop in PythonHow to turn plain-language intent into structured plansHow to use tools and capability layers safelyHow to keep read-only actions separate from mutating actionsHow approval gates and human-in-the-loop design make agents more trustworthyHow structured tool results improve agent behaviorHow to test, evaluate, trace, and debug practical agent workflowsHow to add model-backed planning and ReAct-style reasoning without giving up safety boundariesBuilt around a real projectThis book is centred on exif-privacy-agent, a practical Python agent that can:
Review one image or a folder before sharingDetect privacy-sensitive metadata such as GPS fieldsDecide when cleanup may be usefulAsk for approval before writing filesRun cleanup workflows through a clear safety boundaryUse either a direct local adapter or an MCP stdio capability layerSummarize results for humans while preserving structured outputsWho this book is forThis guide is for:
Developers and builders exploring AI agentsTechnical creators who prefer learning by doingAI builders who want practical agent patterns without hypeReaders who want a clear companion to an MCP server projectAnyone trying to understand how planning, tools, approvals, and safety fit togetherThis is not a research-heavy survey of autonomous systems.
It is not a book about agent swarms or vague AI magic.
It is a focused, hands-on guide to building practical AI agents that are small enough to understand, useful enough to run, and safe enough to trust.
Do you have a question about the book? Login to be able to add your own question.