A Composable Agentic System for Automated Visual Data Reporting
o 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 this https://peter-gy.github.io/VISxGenAI-2025/
Top
- Gyarmati, Péter Ferenc
- Moritz, Dominik
- Möller, Torsten
- Koesten, Laura
Top
Category |
Technical Report (Technical Report) |
Divisions |
Visualization and Data Analysis |
Date |
September 2025 |
Export |
Top
