Walk through Doc-Vision's reconciliation workbench - upload invoices and receipts, connect QuickBooks Online, import account activity as a dataset, match transactions, and build a monthly expense report with Claude Code.
This post shows how to reconcile expense documents to QuickBooks account activity using Doc-Vision.
We explore the reconciliation workbench and connect Doc-Vision directly to QuickBooks Online - so you can pull account transactions into the platform as structured datasets instead of exporting reports by hand.
If you have ever jumped between invoices, receipts, QuickBooks reports, and spreadsheets just to understand what matches what, you know how slow that can get. With Doc-Vision, the workflow becomes much more direct.
In this walkthrough, we upload invoices and receipts, connect QuickBooks Online, import an account as a dataset, and use the reconciliation workbench to review suggested matches and create links. Finally, we use the Integrate Claude Code integration to build a monthly expense report from the reconciled QuickBooks data.
To follow along, go to doc-vision.com, click Start Free, and sign in to get $5 free credit.
Uploading the documents
First, open the Files and Folders app and create a new folder called Expenses.
That gives you a clean workspace for the demo documents, so all invoices and receipts you upload are grouped together.
Next, drag several invoice and receipt files into Doc-Vision. As soon as the documents are uploaded, the platform indexes them and starts extracting structured data from the files.
Instead of treating these as static PDFs or images, Doc-Vision reads the content and turns each document into searchable financial data.
When you open one of the uploaded documents, you can see the extracted fields and line items. Reconciliation does not happen only at the file level - the system works with the actual data inside the document: vendors, dates, amounts, descriptions, and individual line items.
At this point, the expense documents are ready. You still need the other side of the reconciliation: the account activity from QuickBooks.
Connecting QuickBooks Online
Go back to the main menu and open the Integrations app.
Start the QuickBooks connection flow, sign in with Intuit, approve access, and return to Doc-Vision.
QuickBooks remains the source of truth for accounting activity. Doc-Vision stores a structured read model that can be searched, reconciled, and used in workflows.
Once the connection is saved, Doc-Vision can read the available QuickBooks accounts for your organization.
The important part is that you do not need to export a report from QuickBooks and upload it manually. You can pull account data directly into Doc-Vision.
Importing a QuickBooks account as a dataset
Next, import the QuickBooks account you want to reconcile.
Doc-Vision shows the accounts available in QuickBooks Online, and you choose the account you want to use.
When you import it, Doc-Vision creates a new dataset data source for that QuickBooks account and starts the first sync.
The synced transactions are normalized into Doc-Vision as dataset documents. That means each transaction can participate in the same entity layer as uploaded documents and line items.
In plain language, QuickBooks account activity becomes usable data inside Doc-Vision. You can search it, reconcile it, include it in reports, and use it as input for mini apps.
You now have two sets of data in Doc-Vision: expense documents on one side, and QuickBooks account transactions on the other.
Reconciling documents to QuickBooks transactions
Open the Reconciliation app.
On the left, select the document types you want to reconcile: invoices and receipts.
On the right, select the imported QuickBooks account transactions.
That tells Doc-Vision you want to match business expense documents against the account activity that came from QuickBooks.
Notice the Suggested Pairs control at the bottom. The system compares document entities with QuickBooks transactions, mainly by amount, currency, and date.
By default, matching expects the same date and the same amount. If the signs are opposite, you can click the minus control to mark the amount as negative.
Review the suggested pairs, then click Create Links.
The documents are now reconciled and linked to the QuickBooks transactions.
Suggested pairs include close matches, but you can also link items manually by selecting a checkbox on the left and a checkbox on the right. The system auto-fills the amount and currency, so you only need to click to create the new link.
If dates are slightly different, for example because the document date and the accounting transaction date are not the same, adjust the date tolerance and let Doc-Vision find more possible matches.
After a quick review, link the remaining items until the invoices and receipts are reconciled to QuickBooks account activity.
You can save the reconciliation session so next month you can continue from the same setup.
Exporting the reconciliation data
For a traditional reconciliation report format, use the download icon.
That produces a CSV file you can open in any spreadsheet tool.
The CSV is only one option. Because Doc-Vision stores documents, QuickBooks transactions, and reconciliation links as structured data, you can also build richer reporting on top of the same information - which leads to Integrate Claude Code.
Creating a report with Integrate Claude Code AI Builder
Return to the main menu and open the Claude Code app.
Create a new mini app and name it Monthly Expense Report.
Describe what you want Claude to build. The prompt tells Claude to use the reconciled expense data and generate a report that summarizes the month.
Because the QuickBooks account transactions were imported as a dataset, Claude can use the same connected data that you just reconciled.
After you send the prompt, the mini app is generated and rendered in the preview.
You can iterate on the app using natural language, similar to working with an analyst.
Expand the preview and review the completed Monthly Expense Report.
The workflow has gone from raw documents, to connected QuickBooks account activity, to reconciled financial records, and finally to a custom report built on that data.
That is the core idea behind Doc-Vision: financial documents and accounting data should not stay trapped in separate systems. They should become structured, connected data that teams can reconcile, search, analyze, and turn into useful business tools.
With Doc-Vision, the payoff is not only extracting data from documents. It is connecting documents, QuickBooks activity, reconciliation links, and AI-powered tools in a single workflow.
That gives you and your team a quicker read on what has been recorded, what still needs review, and how the same data can feed reporting, analysis, and automation.
QuickBooks integration makes it simpler: account transactions sync straight into Doc-Vision as datasets, so you can reconcile and build on top of them without another manual export.
Doc-Vision is built to automate your financial data and to let you shape custom flows so you and your team can optimize finance operations.
If anything is unclear, leave a comment and we will get back to you.