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

TL;DR

This work observes various prompting and prototyping strategies, highlighting the pivotal role of to-be-generated content characteristics in enabling rapid, iterative prototyping with generative AI.

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.

Figures (10)

• Figure 1: Figure 1. Change in Collaborative Prototyping Process with Generative AI. Before: Expertise (UX, PM, SWE) was siloed for application design decisions, simulating and automating workflows was difficult, uncertainty in AI outputs hindered progress, technical decisions were centralized, user-centered decisions relied heavily on UX/PM, and user interfaces were decoupled from computational functionality during prototyping. After: Generative AI enables expert-guided prompt-based collaboration, accelerates parts of workflows, allows prompt-guided design space exploration, makes technical and design decisions accessible to all roles, fosters collaboration around user needs, and integrates UI with computational functionality during prototyping.
• Figure 2: AI Studio provides text output only; it does not generate user interface screens or source code. However, it includes a "Get Code" feature, which offers a code snippet for integrating the generated prompts into external applications via the model's API. This functionality was not within the scope of our study, as we focused solely on the prototyping process.
• Figure 3: Examples of using LLM as a Collaboration Partner.
• Figure 4: Four Main Components of a Prompt Prototype.
• Figure 5: Example prompts used for need finding using LLM during the collaborative prototyping process.