.png){kind=icon}
What can you ask the AI, and what not? Concrete examples
With the Exact AI Connect connector you ask questions about your bookkeeping in plain Dutch. That works surprisingly well, but not every question produces a usable answer. Below are the most important patterns.
With the Exact AI Connect connector you ask questions about your bookkeeping in plain English. That works surprisingly well for most everyday tasks. But not every question gives a useful answer. Some questions are too vague, others are about things that simply are not in your administration.
Below are the main patterns, so you know right away what to expect.
Questions that work well
Specific lookup questions
The AI excels at targeted questions with clear criteria:
- “Which invoices from customer Jansen are still open?”
- “What is the phone number of supplier Bakker?”
- “Show the last 5 entries on general ledger account 8000”
- “How much stock do we have of item X?”
Why this works: the question is specific enough to determine the right table and the right filter.
Standard financial reports
- “Show the profit and loss statement for Q1”
- “How is the balance sheet looking?”
- “Give an overview of the outstanding accounts receivable”
- “Prepare the VAT return”
Why this works: these are fixed report formats that Exact Online supports as standard.
Comparisons with concrete periods
- “Compare the revenue of March with February”
- “Is the revenue of Q1 this year higher than last year?”
- “Which month had the highest revenue?”
Why this works: the AI can interpret dates and perform calculations on the retrieved data.
Actions with clear instructions
- “Create a new customer: Bakkerij Bloem, Amsterdam”
- “Create a sales invoice for customer X: 3 hours of advice at 150 euros”
- “Update the email address of contact Y to info@voorbeeld.nl”
Why this works: concrete data, no doubt or ambiguity. The AI always shows a preview before it processes anything.
Questions that struggle
Too vague, no concrete criterion
- “How is business going?”
- “Are there any problems?”
- “Give me an overview”
Why not: the AI does not know where to look. “An overview” could be outstanding items, revenue, cash flow or a hundred other things. Rephrase: “Give an overview of the outstanding accounts receivable, sorted by amount.”
Advice and interpretation
- “Should I write this off?”
- “Is this customer reliable?”
- “What should I do to improve my cash flow?”
Why not: the AI shows facts, not judgements. It can show that a customer is 3 invoices late with payment, but the conclusion “this customer is unreliable” is up to you.
Data that is not in Exact Online
- “What does the customer think of our service?”
- “How many visitors did the website have last month?”
- “What are the market prices for raw material X?”
Why not: the connector only gives access to your Exact Online administration. Information from other systems (CRM notes, website statistics, external market data) is not available through this connector.
Future predictions
- “How much revenue will we generate next month?”
- “When will customer X pay their invoice?”
- “How will our margin develop over the coming months?”
Why not: the AI can analyse historical data but cannot predict the future. What it can do: “Show the revenue per month for the past 12 months”, so you can spot the trend yourself.
The borderline cases
Some questions fall in between. They work, but only if you phrase them well:
| Question (vague) | Better phrased | Why better |
|---|---|---|
| “Show the sales” | “Show the sales invoices for this month, sorted by amount” | Period plus sorting makes the question specific |
| “Who pays badly?” | “Which customers have invoices that have been outstanding for more than 60 days?” | Concrete criterion instead of a value judgement |
| “Give me the margins” | “Calculate the gross profit per product group based on SalesInvoiceLines and Items” | Specific tables and calculation named |
| “How much VAT?” | “Prepare a VAT overview for Q1, with supplies and acquisitions listed separately” | Period and level of detail specified |
Rules of thumb
- Ask questions whose answer you can verify. Start with something you know, then build on it.
- Name a period. “Revenue” is vague. “Revenue for March 2026” is concrete.
- Name the location in Exact if you know it. “This prevents the AI from searching in the wrong data for a long time.
- Do not ask for opinions. The AI provides facts, not advice.
- Split complex questions. Three simple questions in a row give more reliable results than one all-encompassing question.
Read in this blog more about what AI can mean for your business administration.
Want to try it yourself? Start for free with Exact AI Connect →
Frequently asked questions
No, the AI shows facts from your records, not judgements. It shows, for example, that a customer pays three invoices late, but the conclusion about whether you want to continue working with that customer is up to you. So ask for concrete criteria rather than opinions.
Usually it comes down to the question itself. With an open question like "give me an overview" the AI does not know which data to search. Name a period, a concrete criterion and, if needed, the place in Exact Online where the data is stored. Three simple questions in a row also work better than one all-encompassing question.
No, the AI only analyses historical data from your bookkeeping and does not make predictions about the future. What it can do is give you the revenue per month for the past twelve months, so you can see the trend yourself and base your expectations on it.
No, the connector only gives access to your Exact Online records. Information from other systems, such as website statistics, CRM notes or external market prices, is not available through this connector. For that data you need a separate source or connector.
No. For actions such as creating a new customer or drawing up an invoice, the AI first shows a preview of what it is going to do. Only after your confirmation is the change actually applied in Exact Online.
