AI-Powered Developer: Build great software with ChatGPT and Copilot

✍ Scribed by Nathan B. Crocker

• Publisher: Manning
• Year: 2024
• Tongue: English
• Leaves: 242
• Edition: 1
• Category: Library

✦ Synopsis

Use groundbreaking generative AI tools to increase your productivity, efficiency, and code quality.

AI coding tools like ChatGPT and GitHub Copilot are changing the way we write code and build software. AI-Powered Developer reveals the practical best practices you need to deliver reliable results with AI. It cuts through the hype, showcasing real-world examples of how these tools ease and enhance your everyday tasks, and make you more creative.

In AI-Powered Developer you’ll discover how to get the most out of AI:
• Harness AI to help you design and plan software
• Use AI for code generation, debugging, and documentation
• Improve your code quality assessments with the help of AI
• Articulate complex problems to prompt an AI solution
• Develop a continuous learning mindset that keeps you up to date
• Adapt your development skills to almost any language

AI coding tools give you a smart and reliable junior developer that’s fast and keen to help out with your every task and query. AI-Powered Developer helps you put your new assistant to work. You’ll learn to use AI for everything from writing boilerplate, to testing and quality assessment, managing infrastructure, delivering security, and even assisting with software design.

About the technology
Using AI tools like Copilot and ChatGPT is like hiring a super-smart and super-fast junior developer eager to take on anything from research to refactoring. Coding with AI can help you work faster, write better applications, and maybe do things that aren’t even possible with your current team. This book will show you how.

About the book
AI-Powered Developer: Build software with ChatGPT and Copilot teaches you in concrete detail how to maximize the impact of AI coding tools in real-world software development. In it, you’ll walk through a complete application, introducing AI into every step of the workflow. You’ll use ChatGPT and Copilot to generate code and ideas, make predictive suggestions, and develop a self-documenting application. You’ll also learn how AI can help test and explain your code.

What's inside
• Use AI to design and plan software
• Code generation, debugging, and documentation
• Improve code quality assessments
• Work with unfamiliar programming languages

About the reader
For intermediate software developers. No AI experience necessary.

About the author
Nathan B. Crocker is Cofounder and CTO at Checker Corp.

✦ Table of Contents

contents
preface
acknowledgments
about this book
Who should read this book?
How this book is organized: A roadmap
About the code
liveBook discussion forum
about the author
about the cover illustration
Part 1 The foundation
1 Understanding large language models
1.1 Accelerating your development
1.2 A developer’s introduction to LLMs
1.3 When to use and when to avoid generative AI
2 Getting started with large language models
2.1 A foray into ChatGPT
2.1.1 Navigating nuances with GPT-4
2.1.2 Charting paths with GPT-3.5
2.1.3 Navigating the AI seas: From the shores of GPT-3.5 to the horizons of GPT-4
2.2 Let Copilot take control
2.3 Let CodeWhisperer speak loudly
2.4 Comparing ChatGPT, Copilot, and CodeWhisperer
Part 2 The input
3 Designing software with ChatGPT
3.1 Introducing our project, the information technology asset management system
3.2 Asking ChatGPT to help with our system design
3.3 Documenting your architecture
4 Building software with GitHub Copilot
4.1 Laying the foundation
4.1.1 Expressing our domain model
4.1.2 Favoring immutability
4.1.3 Decorating our favorite classes
4.1.4 Adapting a strategy for depreciation
4.2 Weaving patterns, patterns, patterns
4.2.1 Paying a visit to our department
4.2.2 Creating objects in a factory (pattern)
4.2.3 Instructing the system on how to build
4.2.4 Observing changes
4.3 Plugging in ports and adapters
4.3.1 Hexagonal architecture in review
4.3.2 Driving our application
4.3.3 Accessing our data and persisting our changes
4.3.4 Centralizing (and externalizing) our data access
5 Managing data withGitHub Copilot and Copilot Chat
5.1 Amassing our dataset
5.2 Monitoring our assets in real time with Kafka
5.3 Analyzing, learning, and tracking with Apache Spark
Part 3 The feedback
6 Testing, assessing, and explaining with large language models
6.1 Testing, testing … one, two, three types
6.1.1 Unit testing
6.1.2 Integration testing
6.1.3 Behavior testing
6.2 Assessing quality
6.3 Hunting for bugs
6.4 Covering code
6.5 Transliterating code—from code to descriptions
6.6 Translating from one language to another
Part 4 Into the world
7 Coding infrastructure and managing deployments
7.1 Building a Docker image and “deploying” it locally
7.2 Standing up infrastructure by copiloting Terraform
7.3 Moving a Docker image around (the hard way)
7.4 Moving a Docker image around (the easy way)
7.5 Deploying our application onto AWS Elastic Kubernetes Service
7.6 Setting up a continuous integration/continuous deployment pipeline in GitHub Actions
8 Secure application development with ChatGPT
8.1 Modeling threats with ChatGPT
8.1.1 Why it matters in today’s development landscape
8.1.2 How ChatGPT can aid in threat modeling
8.1.3 Case study: Simulating threat modeling with ChatGPT
8.2 Scrutinizing application design and identifying potential vulnerabilities
8.2.1 Evaluating design problems
8.2.2 Recognizing common vulnerabilities
8.3 Applying security best practices
8.3.1 Setting the security mindset
8.3.2 Continuous security testing
8.4 Encrypting data at rest and transit
8.4.1 The importance of data encryption
8.4.2 Data encryption at rest
8.4.3 Data encryption in transit
9 GPT-ing on the go
9.1 Motivating theory
9.2 Hosting your own LLM
9.2.1 Baselining with ChatGPT
9.2.2 Asking Llama 2 to spit out an answer
9.2.3 Democratizing answers with GPT-4All
Appendix A Setting up ChatGPT
A.1 Creating a ChatGPT account
A.2 Creating a ChatGPT account with your email address
Appendix B Setting up GitHub Copilot
B.1 Installing the Copilot extension into Visual Studio Code
B.2 Installing the Copilot plug-in in PyCharm
B.3 Taking your first flight with Copilot
Appendix C Setting up AWS CodeWhisperer
C.1 Installing the CodeWhisperer extension into VS Code
C.2 Installing the CodeWhisperer plug-in in PyCharm
C.3 Uttering your first words with CodeWhisperer
index

✦ Subjects

Docker; Application Development; Unit Testing; Integration Testing; Testing; Productivity; Developer Tools; Quality Assessment; ChatGPT; Generative AI; Large Language Models; GitHub Copilot; Prompt Engineering; AWS CodeWhisperer