Data to AI™ / Gemini/Exact Online
Give finance analysts and engineers Exact Online figures inside the terminal and the IDE, so commission runs, budget models and close checks start from the administration, not from exports.
Better answers, fewer tokens.
Gemini CLI
Which customers have the most money stuck in the oldest receivables age group?
Van Dijk Bouw has the most in the oldest group, €14,200 of its €31,500 open total. Across these three accounts, €24,950 sits in Age Group 4.
| Account Name | Total Amount | Age Group 1 Amount | Age Group 4 Amount |
|---|---|---|---|
| Van Dijk Bouw Financial - Aging Receivables List | €31,500 | €9,800 | €14,200 |
| Kessler Logistik Financial - Aging Receivables List | €18,750 | €6,300 | €6,450 |
| Maas Retail Financial - Aging Receivables List | €12,900 | €8,600 | €4,300 |
Read from the current aging list, which reloads all open items on every run. Bucket meaning comes from the Age Group Description fields.
Exact Online is cloud business software for accounting and financial management. Dataddo extracts its receivables aging, payables, sales invoices, budgets and profit and loss data.
Sum Amount DC from Sales - Invoices by Salesperson Full Name for last month and write commissions/2026-09.csv with Invoice Number counts per person.
A finance analyst who runs the commission script from the repo generates its input in one prompt, then reviews the diff against last month's file before the payroll cut-off.
Load Budgets for this Reporting Year into data/budget.parquet with GLAccount Description, AmountDC, Budget Scenario and Reporting Period, one row per account and period.
An FP&A analyst opens the Parquet file in a Python notebook next to the forecast model and compares scenarios there, while Gemini Code Assist helps write the pandas code.
Query the Journal Status List and print the Status of every journal for the current Period as a table, flagging any journal that is not closed.
The controller runs the check in Gemini CLI on the last working day. Only when every journal is closed does the reporting pipeline in the repo get triggered.
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 | |
|---|---|---|---|
| Inputs for finance scripts | Commission and forecast scripts read CSV exports someone downloaded by hand, and nobody knows which day they came from. | Gemini queries Sales - Invoices and Budgets from the latest Dataddo run and writes the input file the script expects. | Scripts fed from the source |
| History of list datasets | Lists such as the Payables list show only today's state, so last month's position cannot be rebuilt later. | Each run reloads the current list, and a dated file Gemini writes into the repo keeps the snapshot under version control. | Positions you can look back on |
| Control over each lookup | A script with Exact Online API credentials can read any administration at any time, unseen. | Gemini CLI asks you to confirm each Dataddo tool call, and Always allow is set per tool, only where you choose it. | Every read approved |
| Which data Gemini reaches | Personal API keys for each analyst spread access to the whole administration across laptops. | Gemini reaches the flows and Contexts attached to AI destinations or AI Models, so finance decides which Exact Online datasets go there. | Access decided in Dataddo |
| Token consumption | Gemini spends tokens exploring raw Exact Online 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 Exact Online 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
|
|---|---|---|
| Financial - Aging Receivables List |
|
Which Account Name rows have a Total Amount above 10,000 in a Currency Code other than EUR? |
| Financial - Payables list |
|
Which Invoice Number entries are past their Due Date and still not approved in Approval Status? |
| Sales - Invoices |
|
Which Invoice Number values for the same Invoice To Name share the same Amount DC and Due Date, possible duplicates? |
| Financial - Outstanding Invoices Overview |
|
What were Overdue Receivable Invoice Amount and Outstanding Receivable Invoice Count at the last run, for a dated snapshot file? |
| Financial - Profit and Loss |
|
What are Revenue Current Period, Costs Current Period and Result Current Year as of the last run, laid out for our close report? |
| Budgets |
|
Which GLAccount Description lines have no budgeted AmountDC yet for the next Reporting Year? |
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 Exact Online sources in Dataddo, such as Sales - Invoices and Budgets, and attach them to a Google Gemini destination or AI Model. In ~/.gemini/settings.json, add Dataddo under mcpServers with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI, then run /mcp auth dataddo and sign in.
No. Dataddo authorizes Exact Online and extracts the datasets. Gemini CLI signs in to Dataddo only, with your Dataddo email and password and MFA if prompted.
No. The Gemini CLI sign-in uses your Dataddo email and password; Google and Microsoft SSO are not offered there. Run /mcp auth dataddo again if a session expires.
Only for the source. Authorize it against the national version you use, NL, DE, BE, FR, UK or US. Once the data is extracted, Gemini queries it the same way for every version.
Yes. Add the Dataddo server to the mcp.json of Gemini Code Assist in IntelliJ. In VS Code, agent mode reads the same settings.json as Gemini CLI.
Date-range datasets re-read a sliding window on each run. Run a full data re-sync once with a wider range, and Gemini can then query the earlier periods.
No. Gemini queries extracted entities through the semantic layer by name. Dataddo never accepts SQL from the model and nothing is written back to Exact Online.
