Software development is one arena where we are already seeing significant impacts from generative AI tools. The benefits are many, and significant productivity gains are currently available to businesses that embrace these tools. A McKinsey study claims that software developers can complete coding tasks up to twice as fast with generative artificial intelligence.
The consultancy’s research found, unsurprisingly, that the use of generative AI hasn’t seriously affected complex coding tasks, so worries about AI replacing programmers can be safely dismissed. However, there are use cases where AI can drastically accelerate team productivity and improve the developer experience.
But before we get into how generative AI tools can make an impact, let’s talk more generally about improving developer productivity using methodologies, frameworks, and best practices. Generative AI is just one tool in a suite of tools.
Measuring and improving developer productivity
Measuring developer productivity, a subset of employee productivity, presents multiple challenges. Traditional metrics, such as lines of code written or hours worked, often fail to capture the intricacies of complex work processes. They may not adequately reflect the quality or wider impact of a developer’s work, and proper assessment may require the inclusion of external factors such as user satisfaction. The key is to recognize that developer productivity extends beyond just generating code; it involves delivering high-quality outputs that consistently satisfy customers while minimizing the risk of attrition. A burnt out developer is usually unproductive.
DevOps Research and Assessment (DORA) metrics, which include metrics such as deployment frequency, delivery time, and mean time to recovery, serve as benchmarks for evaluating the effectiveness of software delivery. These developer productivity metrics empower engineering managers and chief technology officers (CTOs) to accurately measure individual and team performance.
Project management tools, such as the widely adopted Jira, track progress, manage tasks, and facilitate analysis of contributions. Implementing the SPACE framework—software engineering, productivity, analytics, collaboration, and efficiency—offers a holistic approach to software development. Key performance indicators (KPIs), such as story points and real-time productivity tools, serve as benchmarks to consistently measure and improve software developer productivity.
Diversifying productivity measurement beyond individual performance requires a comprehensive understanding of team dynamics. Collaboration platforms like GitHub act as catalysts for a culture of open communication, collaborative code reviews, and easily facilitated pull requests. Such platforms not only allow team members to learn from each other, but also provide a common space for skill enhancement. Strategic introduction of new features and consistent delivery of high-quality code not only strengthen product competitiveness, but also significantly contribute to end-user satisfaction.
DevOps has emerged as a transformative methodology that seamlessly integrates development and operational practices, optimizing the efficiency of the software development lifecycle. By fostering collaboration between developers and operations teams, DevOps aims to streamline processes, reduce time required, and increase deployment frequency. In doing so, it paves the way for an environment conducive to continuous innovation and improvement. DevOps helps address bottlenecks and proactively manage technical debt, enabling a work environment where developers are happy and busy.
Engineering managers can conduct regular input analysis and use this information to integrate new tools and address employee experience issues, creating an environment conducive to developer productivity. The adoption of the YES (Your Engineering Success) model emphasizes the importance of fostering a positive culture of support within the team, fostering an atmosphere that encourages innovation and creativity. This holistic approach ensures that developer productivity is measured and optimized in a way that not only improves individual and team performance, but also fosters the overall well-being of the development workforce.
How generative artificial intelligence can help
There are several ways that AI can streamline development workflows. Here are some other common use cases:
Removing repetitive tasks
Coding often involves simple, sometimes tedious tasks, and this is where generative AI tools tend to shine. Repetitive, routine work such as typing standard functions can be speeded up using auto-completion features. Tools like OpenAI’s Codex can suggest lines of code or entire functions based on natural language descriptions. Code documentation can be accelerated by helping developers automatically adhere to certain documentation formats.
Natural language interfaces
Generative artificial intelligence can facilitate natural language interfaces for software development tools. Developers can be able to interact with development environments, debugging and version control systems using natural language commands, making it more accessible to those without extensive programming knowledge.
Code suggestion
Generative AI can also help beginners by providing context-sensitive suggestions, explanations, and guidance as they write code. This can speed up the learning curve for new developers and democratize the approach to software development.
Code improvement
Generative AI can suggest improvements to existing code by identifying redundant or inefficient parts. This can help maintain code quality and performance over time. Problems that may have been difficult to pinpoint can be found and corrected much faster by implementing AI-suggested solutions, which can even be done automatically.
Code translation
Generative AI can also translate code from one language to another, simplifying code conversion or application modernization projects, such as updating legacy applications by transforming COBOL to Java.
Code testing
Generative artificial intelligence can be used to automatically create test cases. It can analyze code and generate test inputs, helping to improve test coverage and identify potential problems early in the development process.
Error detection
By analyzing large codebases, generative artificial intelligence can help software development teams identify and even automatically fix bugs. This can lead to more robust and reliable software, as well as faster development cycles.
Personalized development environments
Generative artificial intelligence could help create personalized development environments that adapt to individual developer preferences and coding styles. This would increase productivity and make the coding experience more enjoyable for developers.
Improved documentation
Generative AI can help engineering teams generate documentation by summarizing code functionality, explaining algorithms, and providing context. This can be useful for maintaining clear and up-to-date project documentation.
How generative artificial intelligence works for coding software
Generative AI in coding works by using machine learning models that are trained on large datasets of code. These models can understand the structure and syntax of programming languages.
Pre-training the model
Generative AI models are pre-trained on huge datasets containing various examples of code written in different programming languages. During pre-training, the model learns to predict the next word or token in the code sequence based on the context of the previous words. This process allows the model to capture the syntax, semantics, and patterns inherent in different programming languages.
Understanding context
When presented with a coding prompt or query, a generative AI model processes the input and uses its learned knowledge to understand context and intent. The model considers the relationships between different code elements, such as variables, functions, and control structures, in order to generate relevant and syntactically correct code.
Code generation
Using learned patterns and contextual understanding, the generative AI model generates code snippets as output. The generated code is based on the input query and follows the structure and style of the programming languages in which the model is trained.
Adapting to user feedback
Generative AI models often have mechanisms to adapt and improve based on user feedback. Developers can provide feedback on the generated code, helping the model refine its understanding and improve future results. This iterative feedback loop contributes to the model’s ability to generate more accurate and contextually relevant code over time.
While generative artificial intelligence in coding is a powerful tool, it is no substitute for the creativity, problem-solving, and domain expertise of human programmers. It serves as an extension tool, helps developers with coding tasks, provides suggestions, and potentially speeds up certain aspects of the development process. Developers should use generative AI responsibly, thoroughly validate the generated code, and complement its results with their own expertise and understanding.
Hypothetical use case
Imagine a developer tasked with implementing a complex feature for a web application project. Faced with the challenge of intricate data manipulation and dynamic content rendering, it decides to integrate generative artificial intelligence into its development workflow to speed up the coding process. It begins by carefully defining the requirements of a new feature, condensing the underlying logic and structure into a coding query. Using a generative AI tool trained on various web development code datasets, she inputs her coding query, prompting the model to autonomously generate a preliminary code snippet aligned with the specified requirements. This generated code includes functions for data processing, event handling, and dynamic content rendering.
It enters into an iterative process of refinement and fine-tuning of the generated code. Through this interaction, it ensures that AI-generated code adheres to the project’s coding conventions and architectural nuances. With the generated code now to her satisfaction, she integrates it into the existing code base of the web application. Despite the accelerated development process enabled by generative artificial intelligence, it recognizes the indispensable role of human validation in thorough testing to ensure feature correctness, sensitivity and reliability.
Integrating generative AI into her workflow not only speeds up the coding process, but also gives her the ability to spend more time on higher-level design aspects, user experience considerations, and end-to-end testing. This use case demonstrates how generative artificial intelligence serves as a valuable ally, enhancing developer capabilities and contributing to the overall efficiency and quality of the software development lifecycle.
Start of work
IBM watsonx Code Assistant leverages generative artificial intelligence to accelerate development while keeping the principles of trust, security and compliance at its core. Developers and IT operators can accelerate application modernization efforts and generate automation to rapidly scale IT environments. watsonx Code Assistant powers IBM Granite core models that include state-of-the-art large-scale language models designed for code, intended to help IT teams create high-quality code using AI-generated recommendations based on natural language requirements or existing code source.
Explore watsonx Code Assistant
Was this article helpful?
ThatNot