Flint: A visualization language for the AI era

Summary

Microsoft Research AI for Science introduces Flint, a visualization intermediate language for AI-driven chart creation. Flint enables AI agents to reliably generate expressive, visually polished charts from simple, human-editable specifications. It leverages semantic data types to guide the compiler in choosing appropriate scales, baselines, formatting, and color schemes, and automatically manages layout to adapt to data changes. A single Flint specification can compile to Vega-Lite, Apache ECharts, or Chart.js without rewriting, simplifying cross-library deployment. The open-source project includes the flint-chart library and the flint-chart-mcp server, enabling agents to create, validate, and render charts directly in chat or coding environments. This addresses the trade-off where short specs relying on defaults often produce uninspiring charts, while detailed specs are verbose and error-prone, especially for LLMs and agents.