Data to AI™ / Copilot/AFAS
Give the finance department an agent in Teams that answers from current AFAS GetConnectors, so routine questions stop landing in the controller's inbox.
Better answers, fewer tokens.
Microsoft 365 Copilot
Which article groups had the most articles modified last week, and what is their average sales price?
ArtGroup 100 changed most, with 86 articles by ModifiedDate and an average SalesPrice of €42.10. All three groups shown were edited during last week's price update.
| ArtGroup | Articles by ModifiedDate | Average SalesPrice |
|---|---|---|
| 100 Profit_Article | 86 | €42.10 |
| 200 Profit_Article | 54 | €118.40 |
| 300 Profit_Article | 21 | €9.75 |
AFAS has no date range, so each run pulls current articles up to the Limit; the week is counted on ModifiedDate, and Blocked articles are left out of the average.
AFAS Profit is Dutch business software for finance, HR, payroll and CRM. Dataddo extracts whichever GetConnector you have set up in AFAS, with the fields you pick, custom fields included. The supplied GetConnectors shown here, such as Profit_Article and Profit_Employee_Leaves, are examples from the AFAS documentation.
@Office Desk How many Profit_Employee_Leaves records have a StartDate in each week of this quarter, and is next week above average?
Team leads ask the agent in Teams how much leave is planned instead of messaging HR and finance, who keep their time for the exceptions.
@Office Desk Show the average SalesPrice per ArtGroup for the articles in Profit_Article that are not Blocked.
Before the management team meets, a department head asks Microsoft 365 Copilot and brings the price overview into the meeting.
Use the dataddo tools to describe the Profit_Article entity and generate a TypeScript type with ItemCode, Description, ItemTypeCode, SalesPrice and Blocked.
A developer uses GitHub Copilot in Agent mode to keep the internal reporting service in step with the fields the AFAS source actually extracts.
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 | |
|---|---|---|---|
| Routine finance questions | Department heads email the controller for a number, who runs an AFAS export and replies hours later. | The Teams agent reads the AFAS flows from the latest scheduled extraction and answers in the channel. | Fewer requests to finance |
| Which questions reach AFAS | A general assistant guesses at finance questions with no idea which system holds the figures. | The server description in Copilot Studio says the agent holds AFAS finance GetConnectors, so those questions trigger a Dataddo lookup. | Questions routed to the data |
| Field names in code | Developers read sample exports and guess what each column holds and whether it is a number, a date or text. | Copilot describes the entity Dataddo built from the GetConnector metadata, with field names such as ItemCode and SalesPrice, instead of guessing from a sample. | Schema taken from the source |
| Token consumption | Copilot spends tokens exploring raw AFAS 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 AFAS datasets finance and RevOps teams use most, with their real field names. Copilot queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Copilot
|
|---|---|---|
| Profit_Article (example GetConnector) |
|
What is the average SalesPrice per ArtGroup for articles that are not Blocked? |
| Profit_Employee_Leaves (example GetConnector) |
|
How many leave records have a StartDate next week? |
| ProfitGetConnectoren (example GetConnector) |
|
Which supplied GetConnectors with a Naam starting with Profit_ could we add to Dataddo next? |
| Date and key fields |
|
Which records were created on more than a year ago but still have a recent last modified on 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 an AFAS source in Dataddo with your AFAS token, Environment ID and the GetConnector you need, then attach it to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool for https://headless.dataddo.com/mcp-data with OAuth 2.0 Dynamic discovery and publish the agent to Teams.
No. Dataddo extracts whichever GetConnector you have set up in AFAS. Profit_Article and Profit_Employee_Leaves are examples from the AFAS documentation; describe your own GetConnectors to the agent instead.
Through a Copilot Studio agent. Add Dataddo Data Access as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery, then publish the agent via Channels to Teams and Microsoft Copilot.
From the server description you enter in Copilot Studio. Describe the AFAS GetConnectors you extract, for example Profit_Article for prices, so questions about them lead to a Dataddo call.
People you publish it to. In Teams and Microsoft 365 Copilot they type @ and select the agent, which answers from the AFAS flows attached in Dataddo.
Yes. When you authorize AFAS in Dataddo you choose the Environment Type, Profit, Accept or Test, so an agent can be tried on test data before production.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On Business and Enterprise, an admin must first enable MCP servers in Copilot policy.
