Engineering Complex Systems with Generative AI

Catalog description

In his seminal "No Silver Bullet" essay, Turing-Award winner Fred Brooks argued that no single breakthrough—whether technological or managerial—can deliver even a tenfold improvement in software productivity, reliability, or simplicity. This experimental new seminar explores a counter-argument: Could Generative AI deliver improvements of not just one, but multiple orders of magnitude—and if so, how? The seminar investigates the potential and limits of applying GenAI to the development of large and complex software systems that demand production-grade performance, reliability, security, and usability. Participants will survey and debate the current state of the art while undertaking engineering projects carefully designed to explore maximal integration of GenAI in real workflows. Through iterative experimentation, critical assessment, and collective reflection, the course will produce a reusable toolbox of techniques, insights, and best practices aimed at transforming our engineering capabilities.