Data to AI™ / Gemini/QuickBooks
Let finance analysts and bookkeepers who work in the terminal pull QuickBooks invoices, payments and bills straight into notebooks and scripts, with no exports to download and clean.
Better answers, fewer tokens.
Gemini CLI
Which customers owe us the most, and how old is their oldest unpaid invoice?
Northwind Supply has the largest open balance, $19,400, almost as much as the next two customers combined ($22,460). Its oldest open invoice was due on 14 Jul.
| Customer name | Open balance | Oldest Due date |
|---|---|---|
| Northwind Supply AR Aging Detail Report | $19,400 | 14 Jul 2026 |
| Bluebird Studio AR Aging Detail Report | $12,180 | 3 Aug 2026 |
| Harbor Dental AR Aging Detail Report | $10,280 | 21 Aug 2026 |
Open balance comes from the AR Aging Detail Report, which pulls all current data on each run, not from summing invoice history.
QuickBooks is accounting software for small and medium businesses. Dataddo extracts its transactions and standard reports, from invoices and bills to AR and AP aging, cash flow and profit and loss.
From Invoices, export Item Name, Total Amount, Customer Name and Transaction Date for the last 12 months to data/invoices.csv, then show the ten items with the largest revenue change.
A finance analyst preparing a price increase works in a notebook in the repo. The CSV is the input, and the ranking tells her which items to model first.
List every Payments row with an Unapplied Amount above 0 by Customer Name and Transaction Date and write reconciliation/unapplied.md as a checklist.
A bookkeeper runs this in Gemini CLI on Friday afternoon and works through the checklist in QuickBooks, ticking off each payment once it is matched to an invoice.
Group Bills with a Balance above 0 by Vendor Name and week of Due Date for the next eight weeks and save the result to treasury/payables.json.
A finance engineer feeds the JSON into the cash forecast script, and Gemini Code Assist in VS Code updates the loader when the shape of the file changes.
Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
$10.49/month
per seat
3 seats minimum
Flexibly deploy Dataddo in any cloud or hybrid environment.
Custom
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Large transaction histories in code | A homegrown script pages through the QuickBooks API 1,000 rows at a time and breaks when a token expires halfway. | Dataddo loads the history in batches with a data backfill, and Gemini queries the finished flow by entity and field name. | No pagination code |
| Customer names in generated files | A CSV written for analysis carries every Customer Name and lands in a repository more people can read than the books. | Untick customer columns when you create the source, so the files Gemini writes never hold the names. | Repos without client names |
| Control over each lookup | An integration with stored QuickBooks credentials can read the whole company file whenever it runs. | Gemini CLI asks you to confirm each Dataddo tool call, and you pick Always allow only for the tools you are comfortable with. | Each lookup confirmed |
| Token consumption | Gemini spends tokens exploring raw QuickBooks columns, sampling rows and retrying until it understands the data. | Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. | Fewer tokens per answer |
| Answer quality | Prone to wrong joins, invented fields and numbers that are hard to check. | Answers grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The QuickBooks datasets finance and RevOps teams use most, with their real field names. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Invoices |
|
Which Document Number values share the same Customer Name, Transaction Date and Total Amount, possible duplicate invoices? |
| Payments |
|
What is the average Total Amount per payment for each Customer Name over the last six months? |
| AR Aging Detail Report |
|
How many open items of each Transaction type are older than 90 days past their Due date? |
| AP Aging Detail Report |
|
Which Vendor has rows with Past due above 0 but an Open balance smaller than the original Amount, meaning partly paid? |
| Bills |
|
Which Department Name has bills with a Due Date in the past and a Balance above 0? |
| Profit and Loss V2 |
|
What is the Total per Section between Start Period and End Period, as one row per quarter for our model? |
| Cash Flow V2 |
|
Which Account rows in the Financing Section have a total above zero this period? |
| Budgets |
|
What is the total Budget Detail - Amount per quarter, using Budget Detail - Budget Date? |
We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Create QuickBooks sources in Dataddo, for example Invoices, Payments and Bills, and attach them to a Google Gemini destination or AI Model. Add the Dataddo server to ~/.gemini/settings.json under mcpServers with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI and run /mcp auth dataddo to sign in.
No. Dataddo holds the QuickBooks authorization and extracts the datasets you choose. Gemini CLI only reaches the Dataddo MCP server, signed in with your Dataddo account, and never sees QuickBooks credentials.
Check that the server uses httpUrl and not url, since url falls back to SSE, which Dataddo does not support. Restart Gemini CLI, run /mcp auth dataddo and look at /mcp.
The QuickBooks API returns up to 1,000 rows per batch, so load larger histories with a data backfill. Gemini can then query the whole period from the flow.
In ~/.gemini/mcp-oauth-tokens.json. Gemini CLI renews them automatically; if a session expires or is revoked, run /mcp auth dataddo again.
Yes. Add the Dataddo server to the mcp.json of Gemini Code Assist in IntelliJ. Agent mode in VS Code reads the same settings.json as Gemini CLI.
No. Gemini queries extracted entities through the semantic layer by name. Dataddo never accepts SQL from the model and nothing is written back to QuickBooks.
