From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping
For researchers and practitioners in visual analytics, this work provides a method to rapidly prototype ideas, though the findings are based on a single case study and are incremental in nature.
The authors demonstrate that using a workflow language (ATWL) as a scaffold with an AI assistant reduces the time to prototype a visual-analytics idea from months to one afternoon, achieving state-of-the-art quality after expert knowledge injection. Controlled experiments show that providing both a language definition and examples reduces quality due to template following, and scaffolds work best when introduced after an initial unconstrained design pass.
Testing a new visual-analytics idea usually takes months: one needs to find a realistic data set, clean it, and implement an interactive prototype. We describe a case where a workflow language and an AI assistant reduced this effort to one afternoon. The idea under test: relax the Pareto frontier with a tolerance and group the surviving options into recurring types -- ``constellations'' on a ``soft sky''. Using the Artifact--Transform Workflow Language (ATWL) as a scaffold, we obtained a consistent workflow in minutes and a running prototype in a few hours. We derive three lessons. The scaffold matters: without ATWL the assistant produced a naive workflow. The scaffold alone is not enough: the first implementation was only average, and expert knowledge injection was needed to reach state-of-the-art quality. Finally, the way the scaffold is used matters: controlled experiments show that a language definition and a library of examples support different aspects of the task, that providing both at once reduces quality because template following displaces creative content, and that scaffolds work best when introduced after an initial unconstrained design pass. We argue that the field needs a typology of human knowledge injection, in a form that is both human-editable and machine-accessible.