What are you building?
Query every backend through one SQL surface
One SQL path for connection-backed tables, datasets, and SaaS sources registered in your workspace.
Read the guideCreate datasets from CSV and query snapshots
Turn uploads or saved queries into tables that sit next to your connections in the same SQL namespace.
Read the guideRun exploratory SQL inside isolated sandboxes
Scratch space for exploratory SQL and datasets, separate from shared warehouse or staging environments.
Read the guideRun semantic search on embeddings from SQL
Vector indexes, semantic search from the CLI, and nearest-neighbor SQL in the same workspace as the rest of your queries.
Read the guideUpload and filter GeoParquet using spatial SQL
GeoParquet as a dataset with distance, containment, and the rest of your SQL in one engine.
Read the guideControl spend and long-running hybrid queries
Async runs, stored results, connection refreshes, and job visibility without living in the terminal.
Read the guideFind slow SQL in history and add indexes for your filters
Mine query history, inspect tables and columns, then add indexes that match real filters and joins.
Read the guidePublish workspace context for agents
Keep data model and team docs in the workspace so agents and the catalog stay aligned without pasting schemas into every prompt.
Read the guideBuild shared context with your team
A workspace-wide data model plus optional team context, published through the context API and read wherever queries run.
Read the guideCreate full-text indexes and run keyword search from SQL
BM25 indexes, keyword search from the CLI, and BM25-style SQL next to your relational filters.
Read the guideExplore tables and columns before you write SQL
One CLI path to list connections, browse tables and columns, refresh after DDL, and page huge catalogs.
Read the guide