Prototyping with Prompts: Emerging Approaches and Challenges in Generative AI Design for Collaborative Software Teams

TL;DR

This paper explores how collaborative software teams adopt prompt engineering strategies for generative AI, highlighting emerging practices, role shifts, and challenges in rapid, iterative prototyping.

Contribution

It provides empirical insights into new prompt-based design practices and role dynamics in generative AI development within industry teams.

Findings

Emerging prompt engineering practices in industry teams

Role shifts among UX designers, AI engineers, and product managers

Challenges include limited model interpretability and overfitting issues

Abstract

Generative AI models are increasingly being integrated into human task workflows, enabling the production of expressive content across a wide range of contexts. Unlike traditional human-AI design methods, the new approach to designing generative capabilities focuses heavily on prompt engineering strategies. This shift requires a deeper understanding of how collaborative software teams establish and apply design guidelines, iteratively prototype prompts, and evaluate them to achieve specific outcomes. To explore these dynamics, we conducted design studies with 39 industry professionals, including UX designers, AI engineers, and product managers. Our findings highlight emerging practices and role shifts in AI system prototyping among multistakeholder teams. We observe various prompting and prototyping strategies, highlighting the pivotal role of to-be-generated content characteristics in enabling rapid, iterative prototyping with generative AI. By identifying associated challenges, such as the limited model interpretability and overfitting the design to specific example content, we outline considerations for generative AI prototyping.