Sheetgo can extract data from PDF and Google Docs files in a folder. The automation uses AI to turn each document into structured rows in a Google Sheets file.
Create a document extraction automation
Open your workflow and select Add to workflow > Automation.
Choose Folder as the source.
In the Folder field, click Select folder and choose the folder that contains your documents. After selection, use Change folder to choose a different folder.
Under IMPORT SETTINGS, open Content type and select Documents. This removes the tab picker and displays IMPORT OPTIONS.
The default Settings option is Import data from every file in the folder (newest to oldest).
Choose which documents to import
Turn on Filter folder content to choose which files Sheetgo imports on each run. Set Match to all or any, then build conditions with these fields:
File type
File name
Date modified
File content
Select Add condition for another condition. Select Add group to create nested logic.
Under IMPORT OPTIONS, Only import each file once (skip already-processed files) is on by default in Documents mode. Keep it on when you want later runs to process new files without importing processed files again. If a rerun finds no new files, it adds nothing.
The source step also has these options under FOLDER OPTIONS in the advanced settings:
Include files in subfolders
Enable one table per sheet
Tell the AI what to extract
The second step is Process with AI, marked BETA. AI processing is required for documents. This step extracts data from each document into structured rows in your spreadsheet.
Enter the fields and row structure you need in the INSTRUCTIONS box. You can also start with one of the EXTRACTION PRESETS:
Invoices
Receipts
Contracts
Other documents
For example, the Invoices preset fills the instructions with:
Extract each invoice as a row with invoice number, date, supplier, total and tax.
This instruction creates one row per invoice with the columns invoice number, date, supplier, total, and tax.
To create one row per line item instead, tell the AI to extract every line item as one row. A document with three line items then produces three rows. Fields that do not appear in a document remain empty; the AI does not invent values.
Use exact column names
Name every column explicitly when you plan to combine data from several documents. Also tell the AI to keep the names and order unchanged. For example:
Extract every line item as one row. Use exactly these column headers, in this order: invoice number, date, supplier, item, quantity, unit price, line total. Do not add, rename, or reorder columns.
This matters because vague instructions can produce different headings such as Invoice #, Invoice Number, and InvoiceNumber in separate document tabs. Exact instructions produce matching headers, which the Merge processor needs for consistent results.
Set how processing failures are handled
Open the AI step's advanced settings. Under EXTRACTION OPTIONS, set When a document fails to process to Continue with the other files if you do not want one failed document to stop the others. Sheetgo will notify you about files it could not process.
The AI step also offers Connect your OpenAI account for unlimited AI processing. This option uses your key to remove token and data size limits.
Choose the destination
Choose Google Sheets as the destination, then select New file or Existing file. For a new file, complete the File name field. The available FILE TYPE choices are Google Sheets, Excel, and CSV.
Understand the extraction output
Document extraction always creates one tab per source document. Each tab uses the document's name.
The spreadsheet also contains a summary tab with these columns:
Extraction date | File name | Status | Rows extracted | Data tab |
2026-08-25T20:03:20+00:00 | invoice-TEST-001.pdf | success | 1 | invoice-TEST-001 |
Rows extracted shows how many rows the AI created from each document. Data tab identifies the tab that contains those rows.
Prepare a single combined table
Document extraction cannot combine the results itself: it always writes one tab per document plus the summary tab. To create one table, add a second automation that uses the extraction spreadsheet as its source and applies the Merge data processor.
Add another automation to the workflow.
Choose Google Sheets as the source and select the spreadsheet created by the extraction automation.
In the tab dropdown, choose All tabs in the file. Do not tick document tabs one by one: this choice keeps the automation working as the folder grows from four documents to a hundred.
Add Merge data from TRANSFORM DATA.
Under OFFSET HEADER, choose First row to use the first row as the header, or Remove header if you do not want to use it.
Merge data works cleanly when every document tab has the same columns in the same order. The extraction instructions determine that structure, so name and order the columns explicitly. For example:
Extract every line item as one row. Use exactly these columns, in this order: invoice number, date, supplier, item, quantity, unit price, line total. Do not add, rename, or reorder columns.
All tabs in the file also includes the summary tab, whose columns differ from the extracted data. To remove its rows, add another processor after Merge data in the same automation:
On the configured Merge data step, select the control between Processor and Destination. This adds 3 Processor / Select processor.
Choose Filter rows under FILTER DATA.
Set the condition to Column C : Status > Text does not contain >
success, then select Confirm.
This condition removes the summary rows, whose Status cells contain success, while keeping the extracted rows. Because the summary tab is the first merge input, the merged table's row 1 comes from that tab and reads Extraction date, File name, Status, Rows extracted, and Data tab; these labels are not the extracted field names.
Use this same second-processor slot for any further filtering or normalising that the extracted data needs.