10 questions you can ask your own business data – today

The most common objection we hear isn't that AI feels difficult. It's that people don't know what to ask about. As long as the assistant is used to summarise emails and polish text, the value is clear but small. Only when the questions concern your own business – customers, margins, inventory, production – does it start to make a difference day to day.

That's why we have gathered ten questions that our customers put directly to their own data. All of them can be asked today, in Claude or ChatGPT, once the assistant is connected to a semantic model via Vellox MCP. Copy them as they are, or swap the period and dimension for something that fits your business better.

1. Which ten customers did we lose the most revenue on compared with the same period last year – and which item groups account for the drop?

The classic decline rarely shows up in the headline figure. A customer that halves its volumes is hidden behind two new ones that are growing. The breakdown by item group also shows whether the whole account is slipping or just a single product range.

2. Which customers used to order regularly but haven't placed an order in the past 90 days?

A forgotten customer list is usually the cheapest sales initiative there is. Ask the assistant to sort by historical order value, and the sales rep knows where to start calling.

3. How has gross margin per salesperson and customer segment developed over the past twelve months?

Volume is easy to measure and easy to manage towards. Margin is harder – and that's where the difference between a good and a bad deal actually lies. The underlying data comes from the sales module, the same one the management report reads.

4. How much of our suppliers' price increases over the past year have we passed on to customers, by item group?

The question that tends to provoke the strongest reaction in the management team. Purchase prices are adjusted continuously, sales prices in a price list that is updated once a year. The gap in between is pure margin loss.

5. Which suppliers have the worst delivery precision, and which items are hit hardest?

Ammunition for the next supplier meeting. Confirmed delivery date against actual receipt date, by supplier and item – instead of a gut feeling about who tends to be late.

6. Which items tie up the most capital without having moved in the past six months?

Sorted by inventory value, the list becomes concrete immediately. Often a handful of items account for the bulk of the dead capital, and they are rarely the ones you'd guess.

7. Which items risk running out within 30 days given the current consumption rate and scheduled receipts?

The forward-looking variant. The same data, but the question is asked about the future rather than the past – and the answer is something you can act on before the customer gets in touch.

8. Which items show the biggest deviation between calculated and actual manufacturing cost?

The costing is set once and then lives a life of its own. When material, setup time and actual output are compared with the calculation, it quickly becomes clear which items are sold with a margin that only exists on paper.

9. How have scrap and rework developed per production group over the past year?

A trend that rarely has a report of its own, but which often explains why a seemingly stable product has lost profitability.

10. What explains last month's variance against budget – break it down by volume, price and mix?

The hardest question in the monthly review, and the one that usually takes longest to answer manually. With the definitions in place in the model, the breakdown takes seconds instead of an afternoon.

The questions above are easy to ask. What determines whether the answers hold up is what sits underneath them – something we covered more broadly in AI and data that create real impact.

• A semantic model at the foundation. Margin, revenue and inventory value are defined once, in one place. The assistant doesn't recalculate the concepts on its own – it reads the same measures as the management report.

• History that is actually retained. ERP systems often overwrite rather than save. Without retained history, there is no way to answer how something has developed.

• Read-only connection and controlled access. No write operations are possible, and you decide which parts of the model are exposed and to whom.

• Traceability. Every answer can be traced back to measures and dimensions. That's the difference between a decision basis and a guess that sounds convincing.

Always specify the period. "Last quarter" and "year to date" give different answers. Be explicit and you avoid misinterpretation.

Ask for the breakdown up front. Add "per customer group", "per item group" or "per month" to the question. An aggregate is rarely enough to make a decision on.

Ask the follow-up question. The biggest gain isn't in the first answer but in being able to drill further without commissioning a new analysis. "Why did the margin fall precisely there?" is usually the question that leads somewhere.