GenAI for Software Engineering¶
Generative AI (GenAI) is revolutionising software engineering by automating complex tasks and enhancing productivity. It empowers developers to understand and generate complex code, debug errors, and even design parts of systems. Leveraging advances in machine learning (e.g. Large Language Models) can reduce the cognitive load on engineers, allowing them to focus on higher-level problem-solving and more creative aspects of software development.
This is a timely research area as the demand for software and the capabilities of GenAI technologies continue to grow rapidly. With the increasing complexity of modern software systems, traditional development approaches are often insufficient to meet tight deadlines and high-quality standards. Advances in GenAI can help address these challenges by introducing novel tools that adapt to developers' needs, fostering collaboration between human expertise and machine intelligence. This synergy has the potential to redefine the future of software engineering, making it a critical area for research, innovation and knowledge transfer.
I am currently involved in MOSAICO, an international collaborative project which aims to develop an integrated platform and communication protocols that will allow developers to effectively coordinate and orchestrate multiple AI agents. In particular, I am involved in a work-package that designs and implements an LSP-inspired AI-agent server protocol to facilitate efficient, reliable and expandable communication across AI-agent communities.