Leanpub Header

Skip to main content
Go to Leanpub.com

AI-Assisted Software Engineering

Mental Models for Building Software in the Age of Generative AI

AI-Assisted Software Engineering
This book is 100% completeLast updated on 2026-10-23
Antranig Momjian

Generative AI can accelerate implementation, but effective software development still depends on sound engineering decisions. AI-Assisted Software Engineering explores how to distinguish engineering decisions from implementation tasks, decompose development work into well-defined AI-friendly tasks, apply engineering patterns, and use AI to work with unfamiliar technologies and code—all while keeping architecture, requirements, and technical direction under human control.

Minimum price

$9.99

$19.99

You pay

Author earns

$

Also available for 1 book credit with a Reader Membership

PDF
EPUB
WEB
APP
About

About

About the Book

AI-Assisted Software Engineering: Mental Models for Building Software in the Age of Generative AI explores how software engineering changes when generative AI becomes part of the development process.

Rather than focusing on a particular AI tool or prompting technique, the book explores engineering principles, practical patterns, and mental models for working effectively with generative AI.

It examines how engineers can distinguish engineering decisions from implementation work, identify tasks well suited for AI assistance, reduce ambiguity, decompose development work effectively, and build workflows in which human judgment and AI implementation work together.

The central idea is simple: AI should implement engineering decisions—not make them.

Share this book

Categories

Vibe Engineering

Feedback

Contact the author

Author

About the Author

Antranig Momjian

Antranig Momjian, PhD, is a senior software engineer, researcher, and former university lecturer with more than a decade of experience in software development and engineering education.

His experience spans software architecture and the implementation of web, mobile, desktop, and backend applications, as well as cloud technologies and computer systems. He holds a PhD in Engineering from the National Polytechnic University of Armenia and has published research in areas including IoT, telemedicine, software development, and computer systems. He has also authored university textbooks in the field of computer networks.

In recent years, through his work in both industry and academia, Antranig has researched and experimented with how generative AI is changing the software engineering industry and developed practical approaches for using AI to its full potential.

His work on AI-assisted software engineering explores how developers can use AI as a powerful engineering tool while retaining the judgment, architectural thinking, and engineering principles that software development requires.

Contents

Table of Contents

Introduction

  1. A Misleading Debate
  2. What This Book Is About
  3. A Recurring Idea
  4. Practical Examples
  5. The Central Idea
  6. Who This Book Is For

Chapter 1. The AI Shift in Software Engineering

  1. 1.1 A Shift That Is Already Happening
  2. 1.2 Two Misinterpretations of Generative AI
  3. 1.3 History Repeats Itself
  4. 1.4 When Production Becomes Cheaper, Industries Grow
  5. 1.5 The Nature of Software Engineering Is Changing
  6. 1.6 What This Book Is—and What It Is Not
  7. Summary

Chapter 2. Allocating Engineering Decisions

  1. 2.1 What Is an Engineering Decision?
  2. 2.2 Decisions That Should Never Be Delegated to AI
  3. 2.3 Decisions That Can Often Be Delegated
  4. 2.4 Why Large Requests Produce Poor Results
  5. 2.5 Divide Features into Engineering Tasks
  6. Summary

Chapter 3. Recognizing AI-Friendly Tasks

  1. 3.1 Every Feature Is a Collection of Different Tasks
  2. 3.2 From Feature to AI-Friendly Tasks
  3. 3.3 The Decision Boundary: Where Engineering Ends and AI Begins
  4. 3.4 Transforming a Task into an AI-Friendly Task
  5. 3.5 A Complete Example
  6. 3.6 Developing the Skill of Decomposition
  7. Summary

Chapter 4. Reducing Ambiguity: Give AI Tasks With One Correct Direction

  1. 4.1 Reducing the Number of Possible Implementations
  2. 4.2 Do Not Ask AI to Discover Patterns — Define Them First
  3. 4.3 From Screenshots to User Interfaces
  4. 4.4 Build Solutions Incrementally
  5. 4.5 AI Is Not a One-Time Code Generator
  6. Summary

Chapter 5. Expanding Engineering Patterns with AI

  1. 5.1 The First Implementation Is the Most Valuable One
  2. 5.2 Case Study: Creating an Extensible Email Provider Framework
  3. 5.3 Extending Existing Patterns Without Losing Engineering Control
  4. 5.4 Turning Engineering Decisions Into Internal Frameworks
  5. 5.5 Engineering Creates the Multiplier
  6. Summary

Chapter 6. AI as a Knowledge Multiplier

  1. 6.1 More Knowledge Than Any Engineer
  2. 6.2 Onboarding and Exploring Unfamiliar Stacks and APIs
  3. 6.3 Deciphering Legacy Code and Domain Rules
  4. 6.4 The Obsolete Knowledge Trap: When Documentation Changes
  5. 6.5 Knowledge Is Cheap, Judgment Is Irreplaceable
  6. Summary

Chapter 7. AI-Friendly Software Engineering

  1. 7.1 The Codebase Becomes Part of the Conversation
  2. 7.2 Turning Project Knowledge Into AI Context
  3. 7.3 Earning a Place in the Codebase: Review and Responsibility
  4. Summary

Chapter 8. The Economics of AI-Assisted Software

  1. 8.1 When Software Becomes Cheaper to Build
  2. 8.2 Jevons’ Paradox and the Demand for Software
  3. 8.3 Productivity Is More Than Code Generation
  4. Summary

Chapter 9. The Future Software Engineer

  1. 9.1 What Becomes More Valuable
  2. 9.2 Education and Junior Developers
  3. 9.3 Why AI Won’t Replace Developers
  4. Summary

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.)

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.

Learn more about writing on Leanpub