Data Formulator 0.7: AI-powered data analytics for enterprise data

2026-05-28 · Source: Microsoft Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, short

Summary

Data Formulator 0.7 is an open-source AI-powered system designed for enterprise data analytics, addressing challenges of fragmented data workflows and limited coding expertise among analysts. It integrates data connectivity, agent-guided exploration, and visualization refinement within a shared, interactive workspace. The Data Connectors feature establishes governed, reusable connections across diverse sources like databases, warehouses, BI systems, object stores, and local files, significantly reducing integration effort for platform teams. Context-aware AI agents assist users by preparing data, exploring analyses, generating visualizations, and managing complex analytical workflows. These agents access the full analysis workspace, including connected data, tables, and charts, enabling them to reason, write code, and explain steps. An interactive, multimodal interface, featuring a "Data Thread" for historical context and an interactive canvas for direct visualization editing, allows iterative refinement and sharing of analyses without requiring SQL or programming skills.

Key takeaway

For Data Analysts and AI Engineers struggling with fragmented enterprise data and complex analytical workflows, Data Formulator 0.7 offers a robust solution. You should consider adopting this open-source system to centralize data connections and empower your teams with AI-guided exploration and visualization. This can significantly reduce manual integration work and enable iterative analysis without deep coding expertise, accelerating insights and report generation.

Key insights

AI-powered systems can streamline enterprise data analysis by integrating context-aware agents and a persistent, multimodal workspace.

Principles

• AI agents require full workspace context.
• Iterative analysis benefits from persistent history.
• Unified data connections reduce integration effort.

Method

Context-aware AI agents access the full analysis workspace to inspect data, write and run code, generate chart specifications, and explain results, enabling iterative refinement.

In practice

• Establish governed, reusable data connections.
• Automate data preparation and visualization.
• Explore and compare branching analyses.

Topics

• Enterprise Data Analytics
• AI Agents
• Data Connectivity
• Data Visualization
• Open-Source Software
• Iterative Workflows

Code references

• microsoft/data-formulator

Best for: Data Analyst, Data Scientist, AI Engineer

Related on AIssential

• Business Analytics Tools: A Complete Guide for Data-Driven Organizations — Modern business analytics tools integrate AI and leverage lakehouse architectures to meet evolving data demands.
• I Built an AI Agent That Monitors Our Power BI Dashboards 24/7. It Caught a $180K Error at 3 AM. — Automated AI agents can proactively monitor dashboards for discrepancies, preventing significant financial reporting errors.
• d0: Vercel's data analysis agent — Vercel's DZ agent shows 100x growth in PR merges, indicating a fundamental workflow shift.
• An AI-First Approach to Data Engineering with Lakeflow and Agent Bricks — Databricks Lakeflow integrates AI functions directly into ETL workflows for scalable, context-aware data processing.
• What Is a Data Agent? — Data agents transform data interaction from visual reports to natural language Q&A on governed datasets, streamlining insight delivery.
• AI Agent Trends Shaping Data-Driven Businesses — AI agents move business intelligence from passive reporting to active, automated decision-making and workflow optimization.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Microsoft Research.