Why AI Code Fails Without Understanding: Cognitive and Intent Debt in Practice
Details
For this online event, we will have the opportunity to receive Margaret-Anne Storey as a speaker.
After a brief introduction of our community, Margaret-Anne will deep dive on the Triple Debt Model, a framework for reasoning about software health that goes beyond code quality. We will explore Cognitive and Intent Debt in Practice and we will explain why AI-generated code fails without shared understanding.
Abstract:
As generative AI systems take on more of the work of writing and modifying code, many teams are discovering that the core challenge is shifting. The issue is no longer just code quality, but whether teams understand what their systems do and why they were built that way. In this talk, I introduce the concepts of cognitive debt and intent debt, and explain how they emerge in AI-assisted development. I’ll share practical signals for recognizing these issues and discuss how teams can design practices to mitigate cognitive and intent debt.
About Margaret-Anne:
Margaret-Anne Storey is a Professor of Computer Science at the University of Victoria and Canada Research Chair in the Human and Social Aspects of Software Engineering. Her work focuses on developer experience, program comprehension, and how generative AI is changing software development practices.