AI and data that create real impact

AI is fundamentally changing how businesses work, create value and compete. Used correctly, it raises both the pace and the quality of decisions that previously required days of manual groundwork. But real impact takes more than technology.

We see the same pattern at company after company: the AI tools are already in place. Employees use them every day to summarise text, draft documents and clear their inbox. What's missing is the connection to the organisation's own numbers. As soon as the question concerns the business itself – which customers are we losing, what has happened to the margin, how does inventory look – the AI has nothing to work from and starts guessing.

The difference between a pleasant experiment and something that genuinely changes the way you work almost always lies in the data underneath. Not in which model you chose.

An AI answer is never better than the data it is built on. And in most organisations, that data looks something like this:

• business data sits in the ERP system, in tables built for transactions

• key concepts lack a shared definition, so "revenue" means different things

• parts of the truth live in spreadsheets that act as master data

• history is incomplete, because the system overwrites instead of storing

Connect an AI assistant straight to an environment like that and you get answers that sound good but don't hold up. And an answer that sounds good but is wrong is more dangerous than no answer at all – it's rarely discovered until someone has made a decision based on it.

That's why we argue that the AI question is fundamentally a data question. The order matters: structure first, prompt second.

The path there doesn't have to be long, but it does have to be the right one. In short, it's about:

• gathering business data from the systems where it actually originates

• defining the concepts once, so everyone calculates margin the same way

• quality-assuring the KPIs in a model that both reports and AI read from

• opening the model up to AI, instead of letting the AI search through raw tables

• controlling access, so every user only sees what they are meant to see

That is exactly the order Vellox is built for. Your data is retrieved from the ERP system, structured in a semantic model and then used by both your reports and your AI assistant. The same numbers, the same definitions, no matter where the question is asked.

1. Lay the foundation – a semantic model of your business. We retrieve data directly from Business Central, Jeeves, Monitor, Pyramid or Visma Business and structure it in the Vellox data warehouse. The model covers sales, purchasing, inventory, production and finance, and it comes pre-configured for your ERP system from day one.

2. Prompt your data. With Vellox MCP, Claude or ChatGPT connects directly to your semantic model. The assistant understands your modules and KPIs and retrieves current figures instead of guessing. Questions that previously required an analyst and a few hours are answered in seconds – with source data you can go back to and review.

3. Build your own on top. Our REST API serves the same verified data that powers the Vellox modules. That makes it possible to build customer portals, embedded dashboards, automations and your own AI agents without building a new data foundation for every initiative.

4. Keep it responsible. AI applied to business data raises reasonable questions about security and governance. The connection to Vellox is read-only – no write operations are possible – and you decide which parts of the model are exposed and to whom. With the EU AI Act in force, being able to show where an answer comes from also becomes increasingly important. A model with traceable definitions makes that question easy to answer.

5. Make it part of everyday work. The value appears when the controller, the sales manager and the production lead ask the questions themselves. We help with the first use cases, show how to ask and make sure the answers turn into decisions rather than yet another report no one opens.

A few examples of questions our customers ask directly of their own data:

• Which ten customers did we lose the most revenue on last quarter?

• How much of our suppliers' price increases have we passed on to customers?

• Which items are tying up capital in inventory without having moved in six months?

What makes the answers useful isn't that they arrive quickly. It's that they are based on the same figures as the management report – and that whoever receives the answer can ask the follow-up question straight away instead of ordering a new analysis.

If AI feels like something that ought to deliver more than it does today, the model is rarely the problem. More often, it simply has nothing to work with.

Visit www.vellox.se and book a demo, and we'll show you how Claude or ChatGPT answers questions about your specific business – using your own data.