Integrating Generative AI for Quality Engineering into the Software Lifecycle

Software practitioners and development teams are using generative AI and large language models like GPT-4, LLaMA, and PaLM for quality engineering and testing use cases. These include, but are not limited to: software requirements and design validation, test case and test script generation, and test result and coverage analysis. But how effective is generative AI in practice when it comes to delivering software faster without compromising quality? In other words, how do teams effectively apply this emerging technology in practical scenarios? In this paper, we describe an approach for integrating generative AI into the software development lifecycle. Our approach provides a holistic methodology that keeps the human-in-the-loop, while incorporating generative AI tools into communication channels, software hubs, integrated development environments, and test execution and reporting platforms. To keep our discussion grounded in practice, we present industrial case studies in which global teams have used Alita, an enterprise-ready generative AI collaboration platform, for realizing software quality and productivity gains.

Topics:

• Approach to integrating generative AI into communication channels, software hubs, development environments and test reporting tools.
• Benefits, challenges and limitations of integrating generative AI into the software development lifecycle.
• Real-world experiences of leveraging an enterprise-ready generative AI collaboration platform to accelerate global development teams.
  

Anastasiia Udovychenko

Anastasiia Udovychenko is a Lead Software Test Engineer at EPAM Systems, where she supports EPAM's Global Software Testing Practice.

Artem Rozumenko

Artem Rozumenko is a Director of Technology Solutions at EPAM Systems, where he leads initiatives around AI and Machine Learning within EPAM's Global Software Testing Practice.

Ihar Bylitski

Ihar Bylitski is a Director of Software Testing at EPAM Systems, where he leads initiatives around test automation within EPAM's Global Software Testing Practice.

Tariq King

Tariq King is a recognized thought-leader in software testing and quality engineering. He is currently the CEO and Head of Test IO, an EPAM company. Tariq has over fifteen years' professional experience in the software industry, and has formerly held positions including VP, Chief Scientist, Head of Quality, Quality Engineering Director, Software Engineering Manager, and Principal Architect. He holds Ph.D. and M.S. degrees in Computer Science from Florida International University, and a B.S. in Computer Science from Florida Tech. He has published over 40 research articles in peer-reviewed IEEE and ACM journals, conferences, and workshops, and has written book chapters and technical reports for Springer, O'Reilly, IGI Global, and more. Tariq has been an international keynote speaker and trainer at leading software conferences in industry and academia, and serves on multiple conference boards and program committees.