mage: Fluid Moves Between Code and Graphical Work in Computational Notebooks
In collaboration with Carnegie Mellon University, Georgia Institute of Technology
AuthorsMary Beth Kery, Donghao Ren, Fred Hohman, Dominik Moritz, Kanit Wongsuphasawat, Kayur Patel
We aim to increase the flexibility at which a data worker can choose the right tool for the job, regardless of whether the tool is a code library or an interactive graphical user interface (GUI). To achieve this flexibility, we extend computational notebooks with a new API mage, which supports tools that can represent themselves as both code and GUI as needed. We discuss the design of mage as well as design opportunities in the space of flexible code/GUI tools for data work. To understand tooling needs, we conduct a study with nine professional practitioners and elicit their feedback on mage and potential areas for flexible code/GUI tooling. We then implement six client tools for mage that illustrate the main themes of our study findings. Finally, we discuss open challenges in providing flexible code/GUI interactions for data workers.
Agent Seer: Synthesizing Scenarios from Specification Understanding
August 28, 2026research area Data Science and Annotation, research area Tools, Platforms, Frameworks
Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate across conversation turns. Constructing such scenarios by hand demands deep domain expertise, does not scale across tool ecosystems, and produces static benchmarks that cannot track evolving APIs. We observe that tool specifications—function names, natural-language descriptions, and typed parameter…
BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks
August 3, 2024research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)
This paper was accepted at IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) 2024.
Programmers frequently engage with machine learning tutorials in computational notebooks and have been adopting code generation technologies based on large language models (LLMs). However, they encounter difficulties in understanding and working with code produced by LLMs. To mitigate these challenges, we introduce a novel workflow into…
Our research in machine learning breaks new ground every day.