Google Sheets
Read values, update values and formulas, insert rows and columns, and change sheets.
A Google Sheets connection gives a playbook's functions six methods of the Google Sheets API, from a document Auto ships. You sign in to Google and allow Google Sheets, and the connection acts as you: it reads the spreadsheets you can read and changes the ones you can edit.
On Auto Cloud, available once Google's review of Auto completes; on a self-hosted runtime, with your own Google Cloud project, now.
What a playbook can do with Google Sheets
- Read a spreadsheet's structure, and the values of a range.
- Update the values or formulas of a range, append rows, and update several ranges in one call.
- Insert, append, delete, move and resize rows and columns; insert, delete, merge, unmerge, copy, cut and sort ranges; find and replace values; add, duplicate and delete sheets; and change the properties of sheets and of the spreadsheet.
Cell formats, charts, filters and conditional formats are not among the requests the connection offers, so a playbook fills a spreadsheet the team has already formatted.
The tools, as the connection lists them
Tools that read: sheets.spreadsheets.get and sheets.spreadsheets.values.get.
Tools that act: sheets.spreadsheets.values.update, sheets.spreadsheets.values.append, sheets.spreadsheets.values.batchUpdate and sheets.spreadsheets.batchUpdate.
An example workflow
A tracker that fills itself. A schedule trigger runs the workflow every weekday at 06:00. A lookup function reads yesterday's spend and conversions by campaign from a Google Ads connection, and another reads yesterday's sessions by source from a Google Analytics connection. A computation function shapes one row per campaign in the column order the tracker uses, which a lookup function read from the header row. An interaction function appends the rows with sheets.spreadsheets.values.append, so the formulas and charts the team built keep working on the new rows. A reasoning function reads the last seven days and writes two lines of commentary into the "Notes" cell for the day. The run's history in Studio keeps every row read and appended; the tracker shows the figures where the team already looks.
How to connect Google Sheets
- Sign in to Google and allow Google Sheets. The consent screen shows the permissions listed below.
Then:
- Ask your agent to connect Google Sheets to Auto, or open Settings, Agents, Connections in Auto Studio and choose Google Sheets. On Auto Cloud, Studio lists Google Sheets once Google's review of Auto completes.
- On the Studio page, check the service and its access, choose which playbooks may use the connection, and approve it.
- Have your agent check one small read through the connection before a function depends on it.
What it needs
- A Google account, personal or Workspace, with access to the spreadsheets the playbook reads and edit access to the ones it changes.
- Your agent connected to Auto and signed in as you, with permission to change your organization, if your agent adds the connection.
- On a self-hosted runtime, a Google Cloud project of your own with the Sheets API enabled and an OAuth client registered for the runtime, as Let people add connections sets out.
Google grants Sheets as a read scope and a read-and-write scope; the connection's operations delete no spreadsheet, only sheets, rows, columns and ranges within one, where a function names them.
Permissions Auto asks for
- See all Google Sheets spreadsheets.
- See, change, create and delete all Google Sheets spreadsheets.
Good to know
A function that updates or appends values names how Google should read them, as raw text or as a person typing them would, since the API requires it. A range's values are kept in the run's history, where people with access to the playbook can read them.