An Exploratory Study of ML Sketches and Visual Code Assistants

TL;DR

This study investigates how visual sketches in IDEs can be used to generate code for ML workflows, demonstrating that even brief sketches can produce useful code outlines and highlighting potential applications in education and prototyping.

Contribution

The paper presents a prototype Visual Code Assistant that converts developer sketches into Python code using an LLM, exploring its effectiveness and developer perceptions.

Findings

Sketches with diagrams, lists, and numbered points are common in ML workflows.

Brief sketches can generate useful code outlines with high quality.

Positive developer feedback on the tool's usefulness and potential applications.

Abstract

This paper explores the integration of Visual Code Assistants in Integrated Development Environments (IDEs). In Software Engineering, whiteboard sketching is often the initial step before coding, serving as a crucial collaboration tool for developers. Previous studies have investigated patterns in SE sketches and how they are used in practice, yet methods for directly using these sketches for code generation remain limited. The emergence of visually-equipped large language models presents an opportunity to bridge this gap, which is the focus of our research. In this paper, we built a first prototype of a Visual Code Assistant to get user feedback regarding in-IDE sketch-to-code tools. We conduct an experiment with 19 data scientists, most of whom regularly sketch as part of their job. We investigate developers' mental models by analyzing patterns commonly observed in their sketches when developing an ML workflow. Analysis indicates that diagrams were the preferred organizational component (52.6%), often accompanied by lists (42.1%) and numbered points (36.8%). Our tool converts their sketches into a Python notebook by querying an LLM. We use an LLM-as-judge setup to score the quality of the generated code, finding that even brief sketching can effectively generate useful code outlines. We also find a positive correlation between sketch time and the quality of the generated code. We conclude the study by conducting extensive interviews to assess the tool's usefulness, explore potential use cases, and understand developers' needs. As noted by participants, promising applications for these assistants include education, prototyping, and collaborative settings. Our findings signal promise for the next generation of Code Assistants to integrate visual information, both to improve code generation and to better leverage developers' existing sketching practices.