DocsWhat you can doUse it from your tools

For agents

One copy of your data, read by every tool.

Notebooks, Python, DuckDB, Snowflake and Spark read the same open tables. Your agent connects each one with only the access it needs.

  • Agent-guided

Before you start: Claude Code (or any other agent)Data already in LakehouseBoxThe tool you want to use

Say which tools you use

Name the tool and what you want to do with it. Your agent picks the connection and the access level.

Claude Code (or any other agent)Example conversation
You

My sales are already in LakehouseBox (catalog "sales"). I want to analyse them in a Jupyter notebook with pandas on this Mac, and my colleague asks whether she can read them from Snowflake. Set up the notebook part and tell me what Snowflake needs. Follow lakehousebox.com/docs/

Agent · example reply

Now this Mac needs your approval to connect. Approve the connection for the catalog sales. Read access is enough for pandas analysis, so leave write unticked unless you also want the notebook to write tables.

Example replies show what to expect. Your agent adapts to your setup.

Your turn · in the browser

Approve read-only access

Open the link your agent gives you and check the code. This time leave Read selected: a notebook that only analyses data does not need to change it. Approve. You can see and revoke this connection on your account page at any time.

Your notebook, ready to run

Your agent builds the notebook, runs it once and keeps the key out of it.

Claude Code (or any other agent)Example conversation
You

Approved, read only on sales.

Agent · example reply

The notebook works: I ran it end to end and it reads sales.shop.orders (2,938 rows) into pandas.

  • It's in ~/sales-notebook/ with its own Python environment. Open it with jupyter lab sales.ipynb.
  • It starts with revenue by region (Norte first, €262k) and revenue by month.
  • This Mac is connected read-only to sales. The notebook asks for the key when it runs, so the key never appears in the notebook or on screen.
Example replies show what to expect. Your agent adapts to your setup.

Example · verified connection

Read from a notebookNo key in the notebookIn the recorded run: 2,938 rows into pandas with a read-only connection.

Snowflake, Databricks and others

They read the same tables in place, without copying. Some need a one-time step on their side.

Claude Code (or any other agent)Example conversation
Agent · example reply

What Snowflake needs (I couldn't test it here):

  1. A support case with Snowflake, per account, asking them to allow LakehouseBox's storage address. Until then Snowflake refuses the connection. LakehouseBox's own case was approved the next day.
  2. An admin of your LakehouseBox account fetches the setup script for the catalog (my connection is read-only and not an admin).
  3. She runs that script in Snowflake, then adds one statement per table. The data isn't copied; new data appears in Snowflake within about 30 seconds.
Example replies show what to expect. Your agent adapts to your setup.

Each product has its own page under "For agents → Works with": what it can do with LakehouseBox today, what was tested, and its peculiarities. Your agent reads it before it starts.

Why every tool can read the same data

Your tables are Apache Iceberg tables in open Parquet files. Iceberg is a standard that DuckDB, PyIceberg, pandas, Polars, Spark, Trino, Snowflake and Databricks all understand, so each reads the same tables in place, with no export and no copy that goes stale. Each tool connects with its own key, limited to the catalogs and the access you approve.

  • Connect DuckDB on this Mac to my sales, read-only.

  • Write a notebook cell that charts revenue by month.

  • Get the Snowflake setup script for my colleague.