Which BI tools let outside agents write warehouse logic?

Quoted from Databricks’s docsUse this server for development and data engineering: running a specific query you or your coding agent wrote, inspecting schemas, validating SQL syntax, and authoring data pipelines from AI coding tools.

Quoted from Snowflake’s docsProgrammatic creation and querying is possible through interfaces such as JDBC and ODBC drivers or the SQL API.

Quoted from Omni’s docsUse the omni-to-snowflake-semantic-view agent skill to convert an Omni topic into a Snowflake semantic view definition.

Quoted from BigQuery’s docsYou can use the Data Engineering Agent API, which is accessed through geminidataanalytics.googleapis.com, to build, modify, and manage data pipelines to load and process data in BigQuery.

Quoted from Looker’s docs- SQL-based derived analytic models: You define the analytic model by using SQL Data Definition Language (DDL) statements. Looker generates the analytic model within your database by executing the SQL statements that you specify.

Quoted from Metabase’s docsmb logs in to a Metabase instance and lets you or an AI agent read and write content over the Metabase API: questions, dashboards, collections, transforms, and more.

Quoted from MotherDuck’s docsYou can create a Flight with the MotherDuck MCP server: describe the job in natural language, and the agent writes the Python, sets the schedule, and runs it for you with the MCP's Flight tools (create_flight, edit_flight_source, run_flight, and the rest).

Quoted from Mode’s docsCreating, dropping, and altering tables and views

Quoted from Redshift’s docsCreates a view in a database.