Asemic: Designing and Evaluating a Creativity Support Tool for Exploring Form Languages

Most generative AI tools focus on producing single artifacts through slot‑machine–like prompting, limiting creative agency and distancing users from reflective exploration. We instead investigate how a procedural content generation–based tool can support engagement with possibility spaces rather than isolated outputs. Through constructive design research, we developed Asemic (Figure 1 a-c), a generative design tool enabling users to configure and navigate stylistically coherent form languages. We evaluated Asemic through two explorative studies; a qualitative lab study with six participants and an online deployment with 43 respondents. Findings suggest that Asemic supports meaningful exploration of generative spaces and helps users discover coherent families of shapes. However, users also faced challenges regarding fine‑grained control, goal‑directed tasks, and learning the skeleton‑based interface. We contribute insights into agency and roles in generative human-computer interaction, articulate form languages as constructs for designing generative systems, and discuss implications for creativity support tools to empower users as explorers of possibility spaces.