On the Design of AI-powered Code Assistants for Notebooks

TL;DR

This paper explores how to effectively design AI-powered code assistants for computational notebooks, highlighting challenges, opportunities, and user preferences based on surveys and interviews with data scientists.

Contribution

It introduces a design space for notebook code assistants and provides insights from interviews with practitioners to guide future development.

Findings

Disambiguation enhances task accuracy in notebooks.

Domain-specific tools like linters are valuable.

Politeness in assistants improves user experience.

Abstract

AI-powered code assistants, such as Copilot, are quickly becoming a ubiquitous component of contemporary coding contexts. Among these environments, computational notebooks, such as Jupyter, are of particular interest as they provide rich interface affordances that interleave code and output in a manner that allows for both exploratory and presentational work. Despite their popularity, little is known about the appropriate design of code assistants in notebooks. We investigate the potential of code assistants in computational notebooks by creating a design space (reified from a survey of extant tools) and through an interview-design study (with 15 practicing data scientists). Through this work, we identify challenges and opportunities for future systems in this space, such as the value of disambiguation for tasks like data visualization, the potential of tightly scoped domain-specific tools (like linters), and the importance of polite assistants.