Computer programming and software engineering, in general, contribute not only to the tech industry, but to many different sectors of the economy, including commerce, finance, health, transportation, and energy. Software drives the creation of many new products. It increases the productivity of companies through the automation and optimization of processes and enables cost reductions.

As software continues to deliver economic value, new paradigms and tools for software developers have increased the ability to write quality software at a faster pace. Over the last couple of years, GenAI has become one of these tools.

In software engineering, GenAI has suddenly advanced to reach an inflection point and is fundamentally changing the field. This recent technology allows everyone from novices to expert software developers to supercharge their productivity not only in coding but, more generally, the full software development lifecycle (SDLC...

Over the past few short years, LLMs have emerged as the dominant AI resource for writing, research, and inference. They are currently transforming the tech industry, and their applications have a far-reaching impact across all fields. This section provides a brief overview of their unprecedented ascent.

Artificial Intelligence was formally started in 1956 at a famous Dartmouth College workshop of computer science experts. They coined the term artificial intelligence (AI) and set ambitious goals ranging from automated reasoning to natural language processing (NLP). Although the participants expected a rapid progression to these goals, the compute and technology limitations thwarted their success. A publication in 1969 denounced the key technology and allegedly started the first well-documented AI winter, an extended period of no funding or research.

In the 1980s, expert systems emerged as a workable solution where rules could be crafted by technologists...

To deliver quality software, most software teams progress through a series of stages known as the software development lifecycle (SDLC). As shown in Figure 1.1, these steps are designed to be an efficient approach that minimizes the risk of failure. The process usually begins with the recognition of an unmet business need, and cycles through many stages to meet the need with a software system. Projects progress from analyzing the existing state to gathering requirements, designing the system, implementing and testing the code, delivering the solution, and often maintaining the software.

While most people associate software development with coding, actual programming makes up only 25-35% of the overall effort, depending on the type of software and its requirements. The remaining steps are needed to gather requirements, test and document the code, deploy the software, and support its continued functionality, as shown in Figure 1.1.

This book focuses on three separate tools for software development: ChatGPT, OpenAI API, and GitHub Copilot. In 2024, these three tools had roughly a $35 million combined market size for software engineering applications. The market is expected to grow 25% per year throughout the rest of the decade, according to a Research and Markets report. The following chapters of the book will provide instructions on how to subscribe to these services and how to get started. These tools provide distinct kinds of functionality, and knowing when to use which tool is part of the learning curve. Later chapters will highlight the features and use cases for each of the tools.

ChatGPT

OpenAI has been a leader in LLMs since 2015. Led by CEO Sam Altman, the company has produced multiple versions of its Generative Pretrained Transformer (GPT) LLM. While these were well received, the release of ChatGPT in December 2022 transformed the perspectives of AI worldwide.

ChatGPT...

We have been using code completion tools for over a decade, but current GenAI tools are different. We have used the full range of tools, such as keyboard shortcuts, Stack Overflow searches for help, code API search tools, and all the latest refactoring tools and templates available in the IDE. All these strategies have helped us be more efficient in our work, but there has always been a lot of mundane, repetitive work that has limited our coding speed and enjoyment.

The benefits of coding with GenAI

GenAI tools have transformed our output. Within three months of using an earlier version of GitHub Copilot, we were writing code 15% faster. Now, after two years, the combination of GitHub Copilot, ChatGPT, and OpenAI API has supercharged our coding output more than anything else that we have used. We complete twice as much work as we did previously with multiple tools. The improvements in productivity were a combination of advances...

This chapter highlighted that GenAI for coding emerged from the combination of software tool advancements with LLMs. This nascent technology applies not only to coding but can enhance many aspects of the SDLC. The combination of ChatGPT, OpenAI API, and GitHub Copilot provides a complementary set of tools that have been shown to not only improve productivity and enhance code quality but can even bring happiness to programmers.

Although the technology is new and still evolving, GenAI is already changing the software engineering field. This book was developed to provide a structured approach to effectively leverage the tools and achieve the best results across many aspects of the SDLC.

In the next chapter, we will introduce a quick-start guide to OpenAI API and use the chat service for coding tasks. We will build our own code completion program that takes a function’s signature as input and returns its implementation as output.

To learn more about the topics that were covered in this chapter, take a look at the following resources:

• VS Code Plugin: https://github.com/kiteco/vscode-plugin
• Begum Karaci Deniz, Chandra Gnanasambandam, Martin Harrysson, Alharith Hussin, Shivam Srivastava. Unleashing developer productivity with Generative AI: https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/unleashing-developer-productivity-with-generative-ai.
• Alexey Girzhadovich. Scientifically Measuring the True Impact of Generative AI Software Development: https://exadel.com/news/measuring-generative-ai-software-development/.
• Diego Colombatto and Jose Manual Pose Rivadulla. Transforming the software development lifecycle (SDLC) with Generative AII: https://aws.amazon.com/blogs/apn/transforming-the-software-development-lifecycle-sdlc-with-generative-ai/
• Research and Markets Report: Generative Artificial Intelligence (AI) in Coding Market - Forecasts from 2024...