For three decades, the Gang of Four design patterns have shaped how we teach object-oriented software design. Yet, students often struggle to move from pattern recognition to pattern application—understanding not just what a pattern does, but why it fits a given problem. In this lightning talk, I share an approach that brings a new “member” to the design table: the large language model.

By pairing students with GPT-based assistants, we can guide them through a conversational process of design reflection. Instead of using an LLM to generate code, students use it to articulate intent, identify relevant patterns, compare alternatives, and reason about trade-offs. For instance, given a scenario requiring event-driven updates, a student might prompt GPT for potential designs. The resulting dialogue—evaluating the Observer pattern versus Mediator—becomes a structured exercise in pattern-based reasoning.

I’ll present examples from classroom exercises where students critique and refine GPT’s reasoning, reinforcing conceptual understanding through guided reflection. The approach situates LLMs as a cognitive scaffolding tool rather than an answer engine—turning “pattern memorization” into “pattern conversation.”

Attendees will leave with ready-to-implement ideas for integrating LLMs into software engineering pedagogy, emphasizing design literacy, ethical AI use, and critical evaluation. The Gang of Four still have much to teach us—but with GPT, they finally have someone new to talk to.