The Scenario
The engineering manager is onboarding a new team member and the request has landed in your inbox: produce a current data dictionary from the Metabase-connected production database, in an Excel workbook, that the new hire can reference during their first few weeks. The last documented version is sixteen months old. Your Metabase instance has six connected databases and over 140 tables.
The bad version:
- Navigate to each database in Metabase's table browser, click through each table's fields, and manually record field names, types, and descriptions in a spreadsheet.
- Realize about an hour in that Metabase's UI doesn't show all metadata fields in a single view — you have to click into each field individually to see its semantic type.
- Stop at database three and promise to finish the rest next week, knowing you won't.
The documentation gap isn't laziness. It's that building it manually is a full-day project that competes with every other task in the queue.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It can pull Metabase's database and table metadata — field names, types, semantic types, descriptions — and write the full dictionary into the workbook, one worksheet per database.
List all databases in Metabase, then for each database list all tables and their fields with column name, data type, and description, writing everything into this workbook with one worksheet per database
What You Get
- One worksheet per connected database, named after the database.
- Each worksheet has columns: Table Name, Field Name, Data Type, Semantic Type, Description.
- Every field Metabase knows about lands in the workbook — including fields with no description, which land with a blank cell so they're easy to find.
- The structure is consistent across all worksheets, so the new hire can filter and search without jumping between tabs.
What If the Data Is Not Quite Ready
You only need one specific table's schema
Fetch the complete schema for Metabase table ID 47 including all column names, types, and semantic types, and write them into columns A through C of Sheet1 starting at row 1 with headers
Useful for a focused onboarding session on a single high-priority table.
The descriptions are mostly blank and you want to flag them
List all fields for Metabase database ID 2, write field name, data type, and description into this workbook, and in column D write NEEDS DESCRIPTION for any field where the description is empty
The new hire gets an actionable gap list rather than a wall of blank cells.
You need a summary of how many fields each table has
Fetch the schema for all tables in Metabase database ID 2 and write one row per table with table name, number of fields, and the first five field names as a preview
A wide-table warning system — the new hire can see at a glance which tables are complex before diving in.
Full dictionary with gap analysis in one shot
List all databases and tables in Metabase, write every field's name, type, semantic type, and description into a worksheet named for each database, then in a Summary worksheet write one row per database showing database name, table count, field count, and number of fields missing a description
One prompt: the working data dictionary and the documentation coverage report. The engineering manager gets both.
Try It
Get the 7-day free trial of SheetXAI and open the Excel workbook you're building for new-hire onboarding, then ask it to pull the full Metabase schema into worksheets. Also useful: auditing your Metabase workspace inventory, and the hub overview on connecting Metabase to Excel.