Share E-Book
Scan to open this page

Scan with your phone to open this page

Author: Michael Kofler, Bernd Öggl, Sebastian Springer

Rating 3.5 AI initial rating

Generative AI is transforming software development. Stay on the cutting edge with this guide to AI pair programming! Learn how to make the most of modern tools like ChatGPT and GitHub Copilot to improve your coding. Automate refactoring, debugging, and other tedious tasks, and use techniques such as prompt engineering and retrieval-augmented generation to get the code you need. Follow practical examples that show how you can program faster, more efficiently, and with fewer errors with the help of AI. In this book, you’ll learn about: a. Hype versus Reality Learn from expert developers to understand the possibilities (and pitfalls) of AI tools. With the help of practical code examples, see how to use AI helpers correctly to their full potential. b. Assistants for All Tasks This guide gives you an up-to-date overview of all aspects of AI-assisted GitHub Copilot autocompletions, project bootstrapping with OpenHands, debugging and refactoring, application development, and more. c. In the Cloud or Local? Use OpenAI’s API to integrate AI models directly into your own scripts and automations—or use local large language models (LLMs) to work independently of cloud services. Highlights 1) Structured programming with AI 2) Debugging 3) Unit testing 4) Refactoring 5) Automatic document creation 6) Database development and design 7) Scripting and administration 8) Local large language models (LLMs) 9) Retrieval-augmented generation (RAG) 10) ChatGPT and GitHub Copilot 11) OpenHands 12) OpenAI API

AI Reading Assistant

Whole-book reading guide from stratified index samples; jump to passages in the text

AI guide
【One-Line Pitch】 A hands-on field guide for working developers who want to use generative AI tools—ChatGPT, GitHub Copilot, OpenHands, and local LLMs—across the full software lifecycle, from writing functions to debugging, testing, refactoring, and database work, without losing sight of the pitfalls. 【Book Arc】 - **Opening (~0%–12%)**: Frames the "hype versus reality" question, surveys the AI assistant landscape (custom GPTs, fine-tuning, RAG), and gets GitHub Copilot installed and running in VS Code—solving the "where do I even start?" problem. - **Early (~12%–27%)**: Grounds the reader in how LLMs actually work (neural networks, transformers, GPT, context windows, fill-in-the-middle) before moving into pair programming: structuring code into functions, IBAN validation, object-oriented examples, and a quiz project. - **Early–Middle (~27%–38%)**: Applies AI to the daily grind—debugging across web, Flutter, Raspberry Pi, and Visual Studio environments; refactoring with best practices like small steps and test-driven changes; and generating tests, test data, and TDD workflows. - **Middle (~38%–54%)**: Extends AI into documentation (function, class, API, and outdated docs), database design and SQL, administration tasks, and scripting/system administration across Bash, PowerShell, Python, and PHP—plus regex and server setup. - **Late (~54%–…)**: Shifts to infrastructure and independence: running local LLMs with Ollama, Open WebUI, Continue, Tabby, and the Ollama REST API, alongside calling Copilot and ChatGPT from the terminal. (Excerpts do not cover the final chapters on the OpenAI API and RAG in depth.) 【Key Takeaways】 - **AI assistants are productivity multipliers, not magic** (Opening): The book opens by separating realistic capability from marketing hype, using concrete code examples to show where tools help and where they mislead. - **Understanding LLM mechanics makes you a better prompter** (Early): Concepts like transformers, context windows, and fill-in-the-middle explain why suggestions succeed or fail—useful mental models rather than academic theory. - **Pair programming is the core workflow** (Early): Copilot's autocomplete and chat modes are taught through progressive examples—functions, parameters, code reuse, multi-file splits—so you learn by doing, not by reading feature lists. - **Debugging benefits from structured AI dialogue** (Early–Middle): Real scenarios (CSS fixes, Flutter null safety, missing Python modules, exception handling) show how to frame problems so the AI actually diagnoses rather than guesses. - **Refactoring demands discipline** (Middle): The book insists on small steps, unchanged external behavior, clear goals, and test-driven refactoring—AI accelerates the work but doesn't excuse sloppy process. - **Testing and documentation are high-leverage AI targets** (Middle): Generating test data, unit tests, TDD cycles, and function/class/API docs automates tedious work while keeping quality visible. - **AI reaches beyond application code** (Middle): Database design, SQL troubleshooting, PostgreSQL/SQL Server administration, and Bash/PowerShell/Python scripting all get practical prompt examples. - **Local LLMs offer a cloud-independent path** (Late): Ollama, Open WebUI, Continue, and Tabby let you run models locally, with REST API access for integration—important for privacy and offline work. 【Reading Tips】 - **Skim Chapter 1's LLM theory if you already know transformers**—but read the context-window and fill-in-the-middle sections, as they directly affect prompting quality. - **Deep-read the pair programming and debugging chapters** (Early–Middle); these are the highest-density practical examples and reward working through the code yourself. - **Treat refactoring and testing as a paired unit**: the best-practice rules (small steps, test-driven) only make sense together, so read them back-to-back. - **Jump to the local LLM chapters (Late) if privacy or cost matters** to you; they stand relatively independent of the earlier application-focused material. - **Keep a scratch project open**—the book is example-driven, and the IBAN validator, quiz, and scripting examples are designed to be typed, broken, and fixed. 【Coverage Limits】 This guide is based on stratified excerpts covering roughly the first half of the book plus the local-LLM chapters; the OpenAI API integration and RAG chapters are only referenced in the table of contents, so their depth and examples are not assessed here.
Page 2
a- tions are written by the leading experts in their fields. Each book is detailed and hands-on to help readers develop essential, practical skills that they...
View in text
Page 7
.................................................... 77 2.2.2 Checking the IBAN Length .........................................................................
View in text
Page 8
................................... 125 4 Refactoring 127 4.1 Introduction to Refactoring ......................................................................
View in text
Page 6
nclusion ................................................................................................................ 229 8.3 Regular Expressions ..........
View in text
Page 12
.................................................................................................. 305 10.4.4 Trouble with Large Code Files ....................
View in text
Page 14
............................................................... 387 The Authors ................................................................................
View in text
Page 18
cdotes about the major mistakes AI tools have made recently. There are also many chapters in this book in which we show examples with faulty AI code, incorre...
View in text
Page 20
use of AI tools for software development and administration. Clearly, the new developments in the AI sector will have a wide- ranging impact on society, both...
View in text
Tags
AI categories
Artificial IntelligenceProgramming LanguageSoftware
ISBN: B0F488FR6H
Publisher: Rheinwerk Computing
Publish Year: 2025
Language: English
Pages: 363
File Format: PDF
File Size: 3.1 MB
Text Preview (First 20 pages)
Registered users can read the full content for free

Register as a Gaohf Library member to read the complete e-book online for free and enjoy a better reading experience.

Generating text preview…