Data to AI™ / Claude/Exact Online
Controllers and finance leads get straight answers on aged receivables, period results and budget gaps from Exact Online, asked in Claude instead of rebuilt in spreadsheets.
Less tokens, better answers.
Claude
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.
Rank accounts in the Financial - Aging Receivables List by Age Group 4 Amount, and tell me what Age Group 4 Description says that bucket covers.
The credit controller starts the week with the accounts carrying the most in the oldest group, then asks Claude for their open Sales - Invoices before picking up the phone.
Compare Revenue Current Period and Costs Current Period with the Previous Year Period figures in Financial - Profit and Loss, then draft three lines of variance commentary.
At period end Claude lines up current and prior year results from the profit and loss overview, and the controller edits the draft instead of writing it from a blank page.
Describe the Bank Entry Lines entity through the dataddo server, then draft a script that matches GLAccountCode and AmountDC against our ledger export.
A finance engineer in the reporting repository lets Claude Code read the real field list and write the matching logic, without copying bank statement extracts to a laptop.
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.
per seat, billed monthly per seat, billed annually
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Getting Exact Online data into Claude | Someone exports the aging list, the invoice register and the profit and loss overview, then attaches the files to a Claude chat each time. | Claude calls the Dataddo Data Access connector and reads Financial - Aging Receivables List, Sales - Invoices and Financial - Profit and Loss by name. | No attachments to refresh |
| Reading the age groups | Claude sees Age Group 1 to 4 columns in a spreadsheet and has to guess which overdue period each bucket stands for. | Each row carries its Age Group Description fields, and the semantic layer explains every column, so Claude names the buckets the way Exact Online defines them. | Buckets read as defined |
| Building finance code | Engineers keep stale CSV samples of Bank Entry Lines on their machines while they write reconciliation scripts. | Claude Code queries the same Exact Online entities from the terminal after claude mcp add, with credentials kept in the system keychain. | Code built on real field names |
| Access for the finance team | Every analyst works from a personal export, so two people ask Claude and get two different overdue totals. | On Team and Enterprise an Owner adds the connector once, and each member signs in with their own Dataddo account. | One setup, personal sign-in |
| Token consumption | Claude 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. | Less 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. Claude queries them by name through the Dataddo semantic layer.
List of curated datasets
Need a dataset, metric, or attribute you don't see?
Tell us what's missing and we'll add it to the connector.
Runs on your schedule. Date-range datasets re-read a sliding window each run, lists such as Aging Receivables pull all current data, and a full data re-sync loads older history.
Exact Online connector →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 →Set up an Exact Online source in Dataddo for your national version with datasets like Financial - Aging Receivables List, Sales - Invoices and Financial - Profit and Loss. Attach the flow to a Claude destination or AI Model, then add the custom connector https://headless.dataddo.com/mcp-data in Claude, or register it in Claude Code with claude mcp add.
No. Dataddo extracts the Exact Online datasets you select and serves them through the Data Access MCP server. Claude only talks to that server, signed in with your Dataddo account, and never holds Exact Online credentials.
Yes, once the source is authorized against the right national version. If you were redirected to the .nl sign-in, switch to the correct version under Settings > Connected Accounts in Exact Online first, then create the source.
Each row carries Age Group 1 to 4, each with a description and an amount field. Ask Claude to show the Age Group descriptions first, so you know which overdue period each bucket covers before you compare accounts.
Yes. Run claude mcp add with the Dataddo URL, sign in through /mcp and Claude Code queries the same Exact Online entities from your terminal, with credentials kept in the system keychain.
As current as the last scheduled run. Lists such as Financial - Aging Receivables List reload all open items on each run, and Claude can call data_status to state how fresh the data is before quoting a figure.
No. Claude queries extracted entities by name through the Dataddo semantic layer, Dataddo never accepts SQL from it, and nothing is written back to your administration. Bookings still happen in Exact Online.