What problem does it solve?
Helps users quickly analyze, profile, and summarize uploaded tabular datasets by guiding SQL-based exploration, detecting data quality issues, and recommending visualizations so non-expert users can get actionable insights without crafting complex queries from scratch.
Core Features & Use Cases
- Guided data profiling: Lists tables, inspects schemas, reports row counts, samples rows, and computes null rates to surface data quality issues.
- Flexible analysis patterns: Supports aggregation, trend analysis, comparisons, distributions, and Top-N ranking using DuckDB SQL constructs and window functions.
- Visualization guidance: Recommends chart types and produces inline charts for categories, time series, distributions, and bivariate relationships.
- Use case: Quickly profile a newly uploaded CSV or Parquet dataset, identify missing-value hotspots, compute key aggregates, and generate a monthly revenue trend chart.
Quick Start
Ask the agent to profile the dataset, show schema and sample rows for sales.csv, and produce a monthly revenue line chart.