Canvil: Designerly Adaptation for LLM-Powered User Experiences

Advancements in large language models (LLMs) are poised to spark a proliferation of LLM-powered user experiences. In product teams, designers are often tasked with crafting user experiences that align with user needs. To involve designers and leverage their user-centered perspectives to create effective and responsible LLM-powered products, we introduce the practice of designerly adaptation for engaging with LLMs as an adaptable design material. We first identify key characteristics of designerly adaptation through a formative study with designers experienced in designing for LLM-powered products (N=12). These characteristics are 1) have a low technical barrier to entry, 2) leverage designers' unique perspectives bridging users and technology, and 3) encourage model tinkering. Based on this characterization, we build Canvil, a Figma widget that operationalizes designerly adaptation. Canvil supports structured authoring of system prompts to adapt LLM behavior, testing of adapted models on diverse user inputs, and integration of model outputs into interface designs. We use Canvil as a technology probe in a group-based design study (6 groups, N=17) to investigate the implications of integrating designerly adaptation into design workflows. We find that designers are able to iteratively tinker with different adaptation approaches and reason about interface affordances to enhance end-user interaction with LLMs. Furthermore, designers identified promising collaborative workflows for designerly adaptation. Our work opens new avenues for collaborative processes and tools that foreground designers' user-centered expertise in the crafting and deployment of LLM-powered user experiences.