AI dashboard · accounting
QuickBooks Accounting Dashboard
Cash, receivables, spend and profit from one company's QuickBooks Online books, built by Claude through OWOX MCP on eight Data Marts, and checked against the QuickBooks reports: the A/R aging matches to the cent.
Six questions, eight Data Marts
Every view answers one question a CEO asks about the books. Between them they read eight Data Marts loaded daily from QuickBooks Online by a custom connector, and each view names the ones it uses, so the table behind any number is one click away on the QuickBooks data source page.
What this means
Did we do better or worse this month?
Four findings ranked and computed from the rows: where the business made money, where it lost money, the largest opportunity, and the number to read with care, each naming the tables it comes from.
InvoicePaymentBillProfit and Loss report
Cash
How much cash is really free?
Revenue booked, cash collected, bills received and the P&L net income against last month, then cash on hand, the part already spoken for by open bills and card balances, and the free cash left.
AccountBillPayment
Receivables
Who owes us, and how late?
Open receivables in five aging buckets, by customer, with each customer's oldest due date, and days to pay per settled invoice against the Net 30 terms. The buckets rebuilt from invoices match the QuickBooks A/R Aging Summary report to the cent.
InvoiceCustomerPaymentA/R Aging report
Reconciliation
Does the dashboard match the books?
QuickBooks P&L income next to income rebuilt from invoices, and P&L expenses next to vendor bills, month by month, with the gap in each. Invoices explain 94% of income and bills 71% of expenses; the rest sits in tables not loaded yet, named on the page.
Profit and Loss reportInvoiceBill
Payables and spend
Where does the money go?
Spend by vendor this month against last with the change, spend by expense account, and the open bills with how much is already overdue.
BillVendorAccount
Profitability
What does each item earn?
Gross profit by product or service: what it sold for, minus the quantity sold times its purchase cost from the item list.
InvoiceItemGross margin
The figures on this dashboard
Each one is computed once, from the same Data Marts, and read the same way in every view.
Revenue bookedCash collectedFree cashReceivables agingDays to payGross marginP&L coverage
An AI dashboard is only as true as what it reads
Most finance dashboards start from a report exported from QuickBooks. That works until the second export.
On an export
Two exports, two revenue numbers
Each export is its own version of the books, so finance and the dashboard disagree and nobody can say which is right. The file goes to whoever has it, and it is out of date the moment it is saved.
Which one goes to the board?
On your Data Marts
Every view reads the same tables, checked against QuickBooks
Invoices, payments, bills, accounts and the QuickBooks reports land in your data warehouse every day. The dashboard reads those Data Marts through OWOX MCP, and the receivables it shows equal the QuickBooks report to the cent.
One set of books, every view.
Connecting the AI straight to QuickBooks is not enough either. The API returns rows, not meaning: which lines count as revenue, which date to report on, what a deleted invoice looks like. The Data Marts are where that is decided once.
From QuickBooks to a dashboard in five steps
Your analyst does steps one and two once. After that, anyone with access asks their AI for the view they need.
- 01QuickBooks Onlinecustom connectordailyA custom connector in OWOX Data Marts loads the entities and the reports into your data warehouse.
- 02Data Martsone per tableSQL visibleYour analyst defines once what revenue, an open invoice and a settled bill mean.
- 03OWOX MCP and APIgovernedpermissionsThe only door the AI gets: the Data Marts it may read, nothing raw.
- 04Claude or ChatGPTyour own AIAsk for the dashboard in plain words. It builds it on the Data Marts.
- 05AI dashboardrefresh on demandOpen it, press Refresh, and the views re-read the Data Marts.
Build this on your own books
Connect QuickBooks Online, let your analyst define the Data Marts once, and let your AI build the views your team asks for.