This post points to Virginia Tufte’s book on sentence structure, highlighted by Anjney Midha. He argues that AI lab teams should read it before releasing any charts to ensure clear, well-structured communication.

• Anjney Midha recommends AI lab teams read Virginia Tufte's book on sentence structure before releasing any charts
• Sentence-writing principles like cutting unnecessary modifiers, tightening parallel structure, and using punctuation deliberately translate directly to chart design
• A chart lacking narrative structure fails to communicate, just as a sentence missing its verb fails despite looking complete
• Applying these rules means clearer axis labels, concise annotations, deliberate white space, and a logical flow from question to conclusion

This post advises readers who’ve finished Edward Tufte’s work to tackle Jacques Bertin’s principles for quantitative communication. It notes that Bertin’s lessons have guided the reallocation of billions of dollars.

• After finishing Tufte's "Visual Display of Quantitative Information," the recommended next read is Bertin's "Semiology of Graphics."
• Bertin's framework organizes visualization around visual variables—position, size, shape, value, color, orientation, texture—for mapping complex, multi-dimensional data.
• The tweet claims billions of dollars in budget/spending decisions have been reallocated based on lessons from Bertin's text.

ggsql extends SQL so you can write data queries and visualization specs in one composable syntax based on the Grammar of Graphics. It compiles to WebAssembly, works with DuckDB/SQLite and Vega-Lite, and offers an in-browser playground for immediate testing.

• ggsql lets you write a SQL query and a Grammar-of-Graphics chart spec (VISUALISE/DRAW/SCALE/LABEL) in one statement, skipping export-then-plot workflows in Python/R
• It compiles to WebAssembly, runs in-browser via a playground, and currently works with DuckDB/SQLite for data and Vega-Lite for rendering (alpha stage, more connectors/exports planned)
• Its simple, declarative key-value syntax is designed to be easy for both humans and AI tools to generate and inspect

Hex is a unified analytics tool that lets technical and non-technical teams query data, build reports, and deploy dashboards using AI-powered agents. It integrates with common data warehouses, dbt metadata, and offers APIs and Slack/Threads embeds to break down silos. Users cite faster insights, self-serve analytics, and significant revenue impact.

• Hex uses AI agents (Notebook Agent) to auto-generate SQL, charts, and dashboards, cutting report-building time from days to hours.
• Customer claims include one company saving over $100 million and an engineer reporting being "10x faster."
• The NexaCorp sales figures (Teleportation pads, Quantum drives, etc.) are fictional demo data, not real customer results.
• Companies like Notion, Figma, and Mercor use Hex to let non-technical staff self-serve analytics without writing code.

The article outlines five steps to turn AI-generated dashboards from eye candy into actionable tools. It covers defining clear questions, matching chart types to those questions, intentional design (colors, layout, context), narrative flow, and thoughtful interactivity. It also shares prompt examples and tips to enforce these rules in any AI charting tool.

• Before prompting an AI for charts, nail down who's looking, what decision they'll make, and the one key takeaway—otherwise you get eye candy that tells you nothing.
• Match chart type to question: line charts for trends, bar charts for rankings, scatter plots for correlations, and skip pie charts with many slices, 3D effects, dual axes, and spaghetti charts.
• Limit dashboards to five meaningful colors, start bar axes at zero, and add context markers like a WHO guideline line or a COVID-lockdown marker.
• In the WHO air quality example, 93% of cities exceed safe PM2.5 limits, and framing the dashboard as normal levels → problem → improvements (e.g., China's Blue Sky Policy) → next steps turns it into a narrative rather than just charts.

mviz is a Claude skill that simplifies the creation of static reports for ad hoc data analysis by converting compact JSON specifications into professional HTML visualizations. It emphasizes a fast, AI-driven workflow that allows users to iterate quickly, generate reports, and utilize a variety of chart types without extensive coding. The tool works seamlessly with data from various sources, including local files and cloud databases.

• Mviz is a Claude skill that turns compact JSON specs into polished HTML reports/charts, prioritizing speed over BI-style reusability.
• Workflow: build context via natural-language queries (Claude writes the SQL), form a narrative, generate an initial chart, then iterate with follow-up commands.
• Supports many chart types (bar, line, heatmaps, funnels, tables, KPIs) laid out in a customizable 16-column grid.
• Can pull data directly from local files or cloud databases, producing clean, responsive output suitable for print or digital sharing.

Superset is a modern, enterprise-ready business intelligence web application designed for data exploration and visualization. It offers a no-code interface, a powerful SQL editor, and support for various SQL databases, making it a flexible alternative to proprietary BI tools. The platform is highly extensible and built for scalability in cloud environments.

• Offers a no-code interface alongside a powerful SQL editor, appealing to both business users and analysts
• Supports a wide range of SQL databases, positioning it as a flexible alternative to proprietary BI tools
• Built to be highly extensible and scalable for cloud environments