Data to AI™ / Copilot/Exact Online
Sales managers and finance staff check invoice status, unpaid receivables and cash due in Teams through one Copilot agent that reads your Exact Online figures.
Less tokens, better answers.
Microsoft 365 Copilot
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.
@Exact Finance Desk Are any Sales - Invoices for Invoice To Name Kessler Logistik past their Due Date? Show Invoice Number and Amount DC.
Account managers mention the finance agent in their Teams channel to see whether a customer has paid, instead of messaging the bookkeeper and waiting for a reply.
@Exact Finance Desk Total Receivables Amount DC with a Due Date in the next 30 days against Payments due in the same window, and give the net.
The finance manager asks in Microsoft 365 Copilot for incoming against outgoing cash for the coming month and copies the summary into the weekly cash update.
Use the dataddo tools to describe Exchange Rates, then list Source currency, Target currency, Rate and Start date for our conversion module.
A developer on the reporting pipeline asks GitHub Copilot in Agent mode for the real rate fields, so currency conversion code uses Exact Online names instead of guesses.
Data to AI™ is free while in private pre-release. We onboard teams in waves and shape the product with their feedback. At launch, it will be priced like the AI assistants your team already uses. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
Free during pre-release
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 | |
|---|---|---|---|
| Invoice questions from sales | Account managers message the bookkeeper to ask whether a customer paid, and the bookkeeper looks it up in Exact Online by hand. | A Copilot Studio agent published to Teams answers from Sales - Invoices, so the account manager mentions it in the channel and gets the status. | Fewer status requests to finance |
| When the agent calls Dataddo | A generic Copilot chat answers finance questions from general knowledge, with nothing tying it to your administration. | The server description tells the agent that invoices, receivables and payables live in Dataddo, so those questions trigger a lookup. | Lookups on the right questions |
| Several divisions | Each division is exported separately and pasted into the chat, so group totals depend on who collected which file. | Multi-account extraction collects a dataset from every entity you can access, and the agent splits figures by the Division field. | All divisions in one agent |
| Developers and finance data | Developers ask finance for sample exports to learn field names for Exchange Rates and transaction lines. | GitHub Copilot in VS Code describes the entities through .vscode/mcp.json, so code follows the real Exact Online fields. | No sample exports needed |
| Token consumption | Copilot 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. Copilot 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 →Extract Exact Online datasets such as Sales - Invoices, Receivables and Payments with Dataddo and attach them to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool pointing to https://headless.dataddo.com/mcp-data, sign in with OAuth 2.0 Dynamic discovery, then publish the agent to Teams and Microsoft 365 Copilot.
Through a Copilot Studio agent with Dataddo Data Access as its MCP tool. Publish it via Channels > Teams and Microsoft Copilot, and users mention it with @ in chats and channels to ask about invoices or receivables.
The agent uses the description to decide when to call Dataddo. Mention invoices, receivables, payables and profit and loss from Exact Online, so finance questions trigger a lookup while unrelated chat does not.
Yes. Add the Dataddo URL to .vscode/mcp.json with type http, start the server and sign in, then use Copilot Chat in Agent mode. On Copilot Business and Enterprise an admin must enable the MCP servers in Copilot policy.
Yes, if the flows hold them. Multi-account extraction collects a dataset from every entity you can access, and the agent can split figures by Division where the dataset has that field.
Start with what people ask about most: Sales - Invoices for status questions, Receivables and Payments for cash due, and Financial - Profit and Loss for results. Attach only the datasets the agent's audience should see.
No. The agent only reads extracted data through Dataddo. Approval Status in the Payables list can be queried, but approving or changing an invoice still happens in Exact Online itself.