- Preface
- Introduction
- Chapter 1 — From Language Models to Agent Engineering
- Chapter 2 — Building with Antigravity
- Chapter 3 — Gemini Models and Context Engineering
- Chapter 4 — Your First Agent with ADK
- Chapter 5 — Skills and Reusable Agent Capabilities
- Chapter 6 — Structured Outputs and Agent Contracts
- Chapter 7 — Tool Engineering
- Chapter 8 — Evidence-Backed Research with MCP
- Chapter 9 — Multi-Agent Workflows and Human Approval
- Chapter 10 — Evaluate, Deploy, and Demonstrate
- Chapter 11 — Loop Engineering with ADK
- Book 1 Conclusion
- Introduction to Book 2 — Advanced Agent Architectures
Agent Engineering with Gemini
Book 1: Build an Inspectable Agent MVP with Gemini, ADK, and Antigravity
This book is 30% completeLast updated on 2026-07-25
Move beyond agent demos and learn to engineer reliable AI systems with Gemini, ADK, and Antigravity. Build the WidgetWare SDR while mastering context, tools, skills, structured workflows, evidence-backed research, multi-agent coordination, human approval, evaluation, deployment, and controlled loops. Includes all future Early Access update
Minimum price
$19.99
$29.99
You pay
Author earns
PDF
EPUB
About
About the Book
Agent Engineering with Gemini is a practical guide to designing and building reliable AI agents—not merely impressive demonstrations.
Most material about AI agents focuses on prompts, framework syntax, or isolated examples. This book focuses on the engineering discipline surrounding the model: context, tools, reusable skills, structured workflows, control loops, evaluation, guardrails, and human oversight.
Book 1 takes readers from first principles to a complete, inspectable agent MVP using Google Gemini, the Agent Development Kit (ADK), and Antigravity.
Throughout the book, readers build the WidgetWare SDR, an evidence-backed sales-development agent for a fictional company. The system researches target organizations, identifies relevant business signals, develops stakeholder and pain hypotheses, prepares personalized outreach, evaluates its own work, and pauses for human approval before any external action.
Readers will learn how to:
- Distinguish prompts, assistants, workflows, and agents
- Decide when an agent is—and is not—the right solution
- Structure an agent-development workspace with Antigravity
- Give agents relevant business context and durable instructions
- Design tools with narrow permissions and predictable outputs
- Package reusable capabilities as skills
- Build structured workflows with Gemini and ADK
- Implement evidence-backed research and traceable claims
- Coordinate specialist agents through explicit handoffs
- Add evaluation, guardrails, and human-approval boundaries
- Integrate the components into a working WidgetWare SDR MVP
The book emphasizes one central principle:
Use deterministic software wherever the required behavior is known. Use an AI agent only where interpretation, judgment, uncertainty, or adaptive reasoning genuinely requires it.
This book is intended for software engineers, architects, consultants, technical leaders, instructors, product builders, and students who want to move beyond prompt experimentation and learn how complete agent systems are engineered.
This is an actively developed Early Access Edition. Book 1 is designed as a complete 10-class learning journey supported by implementation exercises and a companion reference project. Purchasers receive future updates to this edition, including improved explanations, corrections, examples, exercises, and lab updates.
Author
About the Author
Venkatesh Tadinada
Venkatesh Tadinada is an AI engineering leader, enterprise architect, educator, and entrepreneur with more than 25 years of experience across data engineering, business intelligence, cloud computing, machine learning, and generative AI.
He has held senior consulting and technology leadership roles, including at Ernst & Young, and has participated in two successful technology startup exits. He has designed and delivered enterprise systems across industries and advises organizations on AI strategy, architecture, governance, and production implementation.
As Head of AI Consulting at CloudKarya, Inc., Venkatesh focuses on turning promising AI prototypes into reliable, secure, and production-grade systems. He also teaches cloud and generative AI engineering, emphasizing first principles, engineering judgment, evaluation, observability, and operational discipline.
Agent Engineering brings together these lessons in a practical framework for developers, architects, consultants, technical leaders, and product builders who want to move beyond impressive demonstrations and build AI agents that can be trusted.
Contents
Table of Contents
Get the free Community Edition
You can get the free Community Edition in PDF or EPUB just by sharing your name and email address with the author, or you can just click this link to read a shorter sample online...
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
See full terms...
Earn $8 on a $10 Purchase, and $16 on a $20 Purchase
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
In fact, authors have earned over $15 million writing, publishing and selling on Leanpub.
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
Write and Publish on Leanpub
You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!
Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.
Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.