# Jupybara: Operationalizing a Design Space for Actionable Data Analysis and Storytelling with LLMs

arXiv: https://arxiv.org/abs/2501.16661 · HTML: https://mlsanity.com/paper/2501.16661/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2025.

## Built on by (most cited first, 5 of 5)

- [Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems](https://mlsanity.com/paper/2505.19101/) (2025)
- [GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning](https://mlsanity.com/paper/2505.21863/) (2025)
- [DATAREEL: Automated Data-Driven Video Story Generation with Animations](https://mlsanity.com/paper/2604.25220/) (2026)
- [JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models](https://mlsanity.com/paper/2512.06859/) (2025)
- [AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis](https://mlsanity.com/paper/2608.17834/) (2026)

## Abstract (arXiv)

Mining and conveying actionable insights from complex data is a key challenge of exploratory data analysis (EDA) and storytelling. To address this challenge, we present a design space for actionable EDA and storytelling. Synthesizing theory and expert interviews, we highlight how semantic precision, rhetorical persuasion, and pragmatic relevance underpin effective EDA and storytelling. We also show how this design space subsumes common challenges in actionable EDA and storytelling, such as identifying appropriate analytical strategies and leveraging relevant domain knowledge. Building on the potential of LLMs to generate coherent narratives with commonsense reasoning, we contribute Jupybara, an AI-enabled assistant for actionable EDA and storytelling implemented as a Jupyter Notebook extension. Jupybara employs two strategies -- design-space-aware prompting and multi-agent architectures -- to operationalize our design space. An expert evaluation confirms Jupybara's usability, steerability, explainability, and reparability, as well as the effectiveness of our strategies in operationalizing the design space framework with LLMs.