A Composable Agentic System for Automated Visual Data Reporting
By: Péter Ferenc Gyarmati , Dominik Moritz , Torsten Möller and more
Potential Business Impact:
AI and people work together to make reports.
To address the brittleness of monolithic AI agents, our prototype for automated visual data reporting explores a Human-AI Partnership model. Its hybrid, multi-agent architecture strategically externalizes logic from LLMs to deterministic modules, leveraging the rule-based system Draco for principled visualization design. The system delivers a dual-output: an interactive Observable report with Mosaic for reader exploration, and executable Marimo notebooks for deep, analyst-facing traceability. This granular architecture yields a fully automatic yet auditable and steerable system, charting a path toward a more synergistic partnership between human experts and AI. For reproducibility, our implementation and examples are available at https://peter-gy.github.io/VISxGenAI-2025/.
Similar Papers
Multi-Agent Data Visualization and Narrative Generation
Artificial Intelligence
Automates data stories, making insights easier to share.
Designing a Lightweight GenAI Interface for Visual Data Analysis
Human-Computer Interaction
Lets you ask computers questions about data easily.
Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework
Artificial Intelligence
Lets anyone ask computers about business data.