Ground → your workflow
Generate once. Keep going where you work.
Open a completed export and choose Use dataset. Each destination reuses those rows and their saved version.
First implementation: source installation required for SDK/CLI/MCP. Browser notebook download works with your signed-in session. Public package releases, hosted OAuth and client marketplaces remain planned.
Use a Ground export in Python or a notebook
Continue from Ground’s completed export into Jupyter, Colab or VS Code without generating another dataset.
Setup, run and verifyTurn a Ground export into a SQL fixture
Load the same exported rows into PostgreSQL or a new SQLite database, preserving saved types and detected simple keys.
Setup, run and verifyUse Ground from your coding agent
Run a local stdio MCP server or CLI over Ground’s existing API, then inspect and save the same completed export in your project.
Setup, run and verify