Can I Offer You Corrupted Data Gruel?

Imagine walking into a new restaurant. A digital AI chef in a spotless apron approaches you, brimming with confidence and a convincing smile. He radiates such professionalism that you trust him instantly – thinking to yourself that you might have just stumbled upon a hidden Michelin-starred spot that nobody else knows about yet.

He places a plate in front of you and says with great passion: “Here you go, this is exactly the information you ordered, bon appétit.”

The presentation looks flawless, almost like a work of art. But as soon as you examine the plate more closely, you know something is amiss. The ingredients seem completely out of context with the order, and it is clear that no recipe was used. When you take a bite, your suspicion is confirmed – the flavor is distorted.

Indeed, what a chef needs to serve a good meal varies. In reality, it all depends on his access to high-quality ingredients and clear recipes – or in other words: context and understanding of the data he works with.

This is exactly what happens when AI is unleashed on your data without context. It is just like this self-satisfied chef: it is nothing but confidence and always sounds like it knows what it is doing. It can generate professional-looking answers presented with great conviction, but without guidance, the content is nothing but beautifully presented digital data mush.

Data is raw material - not a finished meal

We regularly hear that data is valuable and crucial, but having a lot of it does not achieve anything on its own. In traditional business operations, all kinds of data accumulate here and there. We store them in databases, documents, and various systems we use day-to-day. We try our best to keep track of and categorize them to make them accessible later.

However, this is like having a lot of raw ingredients for cooking; they do not yield a good meal unless processed with knowledge. No matter how fancy the databases or archives are, this context is often missing to prepare good information. Data storage is primarily a technical challenge, but giving them meaning and creating context is what transforms raw material into real value.

A recipe for success: Infrastructure that supports decision-making

If we want to ensure our AI chef meets expectations, we must view technology as the tools in the kitchen. Many new and unfamiliar words accompany the AI wave, but at their core, they are all about the same thing: ensuring the chef understands the order, finds the right ingredients, and uses his knowledge to prepare a good meal.

But a good restaurant is of little use if there are no customers. It is indeed the guests who judge the quality of the food. They have expectations, and they are the ones who decide whether the order was delivered correctly on the plate. If the guest does not get what they ordered, it does not matter how fancy the presentation is.

To make the guests' experience as good as possible, we need to introduce a few new tools into the kitchen's organization:

• RAG (The chef's reference book): Think of RAG (Retrieval-Augmented Generation) as the difference between two chefs:

  • Chef without RAG: He learned everything in school five years ago. If you ask him: “How much salmon do we have left?” he is forced to guess, because he hasn't checked the inventory today. He might say with great confidence: “There is plenty of salmon,” even if they are completely out.

  • Chef with RAG: He has a tablet in hand connected directly to the inventory system. When you ask him about the salmon, he starts by checking the screen, retrieves the results, and then answers: “We have exactly 4.2 kilograms of salmon.”

• System Prompts: Think of this as the chef's established working rules. They tell him exactly how to behave towards guests and how to interpret orders so that the experience is always consistent.

Example: “We never use cilantro in this dish, and all fish must be served with lemon.” This ensures the chef always follows the restaurant's rules rather than making up his own rules every time someone orders food.

• Data model and organization (The storage room itself): For the chef to work systematically, access to ingredients must be good. If access is time-consuming and labeling is incorrect, it can significantly impact efficiency and increase the likelihood of errors. The technicians working with the AI can do a lot to pave the way to the right ingredients, but sometimes data specialists simply need to be called in to make improvements.

• Pre-processing ingredients (Staging and ETL): Just like in fine restaurants, it is important to prepare the ingredients before the order comes in. We call this ETL (Extract, Transform, Load). We retrieve data from core systems, such as enterprise resource planning (ERP) systems, transfer them to a “staging” layer, and clean them there.

  • Example: This is like rinsing the sand off the lettuce and peeling the potatoes beforehand. This way, the ingredient is ready for the pot when the chef needs it, relieving pressure on primary systems and ensuring the AI works with correctly handled data.

• Structured ingredient storage (The Warehouse): Instead of the chef having to search through a giant and chaotic warehouse where items are stored based on when they arrived, data specialists reorganize the storage into a data warehouse. A query layer is created there, modeled after the menu (the company's business model).

  • Example: We arrange the ingredients on shelves (dimensions). One shelf is for meat products, another for vegetables, and the third for dairy. Instead of searching through thousands of boxes for tomatoes, the chef knows exactly which shelf to go to in order to access the right ingredient.

• Semantic Layer: This is where technology, business intelligence, and context meet. This layer ensures everyone understands terms the same way, regardless of how the question is phrased.

  • Example: Instead of the chef needing to know a complex mathematical formula, we create a common context like “Sales excl. VAT” or “Quantity sold.” The AI simply asks for “Sales” and always gets the pre-determined figure, e.g., “Sales excl. VAT.”

• The inventory manager at the hatch (MCP and API): MCP (Model Context Protocol) is the latest technology in AI projects today when it comes to integrations. It works like an inventory manager who handles delivering what the chef needs through a service hatch (API). We place these service hatches on top of our data to make them more accessible, so the chef always gets the right ingredients based on his requests.

Example: Instead of the AI chef having to search everywhere themselves for ingredients in the warehouse or other systems, he asks the inventory manager (MCP) for the ingredient. The inventory manager knows exactly where everything is, retrieves it, and hands it to the chef through the service hatch (API). This increases speed and security, while creating context that prevents the chef from “improvising” with all sorts of ingredients he finds at any given moment (what is called hallucinations in AI).

• From information to execution (Agents): But the system can do more than just retrieve ingredients to answer queries. By adding Agents, the inventory manager gets executive power. He can not only answer questions but also perform tasks independently, such as automatically ordering new ingredients when he sees stock is running low.

Even though we are talking about many new concepts today, and even reviving old concepts that have gained a new role and increased importance in the context of AI, one thing remains unchanged: careful needs analysis is always a key prerequisite for success. Whether it is RAG, MCP, data models, or traditional data processing, the best solutions must be evaluated in each case. The choice of tools is not determined by what is newest or most prominent, but by the complexity of the project, its scope, and the decisions it is meant to support.

Is your restaurant ready to take orders?

As previously stated, it matters little how smart and convincing the “chef” is if he has neither clear recipes nor access to the right ingredients. Without context, definitions, and secure access to data, the experience is often beautifully presented — but wrong.

AI does not solve problems that already exist in the data. It simply makes them more visible. When given incorrect assumptions, it nevertheless answers with great confidence. There is a reason why distorted data mush often looks better than it tastes.

The solution does not lie in a single technological layer, but in the synergy of:

• AI specialists, who bring new tools and knowledge
  
  

• database and data specialists, who know the raw materials well
  
  

• the business side, which defines what a “correct answer” actually means
  
  

How do we open the kitchen?

A common misconception is that everything must be perfect before starting. The reality is different. Most companies can open the kitchen gradually and purposefully, without reorganizing everything.

Often, you can start with three simple steps:

Start where the need is real

Choose a use case that touches daily operational decisions — for example, inventory levels, sales figures, or other key information. The goal is not to answer all questions, but those that really matter to people who need information quickly and securely to make decisions.

Open a secure path to data

Instead of waiting for a perfect data model, you can open and manage access control to existing data. This can be through an API, MCP, or other methods.

The most important thing is not how the data is retrieved, but that both users and AI always work from the same assumptions. With such an approach, it is also possible to “stir the soup” before it is served: personally identifiable data is filtered out, sensitive information is protected, and trade secrets are prevented from accidentally becoming accessible. This ensures that access is not only efficient, but also secure and compliant with data protection and confidentiality regulations.

Incorporate operational knowledge from day one

AI specialists and technical teams know how to connect to data and work with the tools. But it is the operational specialists who know what the answer should mean and how it is actually used.
This knowledge resides with people who have worked with the processes for years — in finance, operations, sales, service, or IT. It does not necessarily reside in data models, but in experience, exceptions, and unwritten rules.

When these three steps are taken, the AI's answers will not only be technically correct, but also usable for operational purposes.

APRÓ supports your company on the data and AI journey

APRÓ is a leader in implementing the latest technology when it comes to data context and the practical application of AI. We have one of the country's most capable teams covering the entire process – from organizing the “ingredient storage” to designing the “digital chef.”

We employ specialists with extensive expertise in:

• AI and Agents (AI Agents): We design and implement solutions like RAG and MCP to ensure that the AI delivers the desired results,

• Databases and data processing: Our experienced data specialists and data engineers take care of cleaning, organizing, and modeling your data (ETL/ELT) so that the AI can use it.

• Cloud Solutions (AWS and Azure): We are specialized partners in both AWS and Azure. We leverage powerful infrastructure, whether it is Amazon Bedrock or Microsoft Foundry, to run AI projects securely and scalably in the cloud environment that suits you.

We help companies bridge the gap between complex technical solutions and business needs. Whether you need to organize large datasets or want to build your first “service hatch” in AWS or Azure, our team is ready to guide you through the process – from initial analysis to a completed solution.

Are you ready to turn data mush into a great meal? Let's find the right recipe for success in your business together. Get in touch, and we will show you how to leverage your data with the latest AI technology, regardless of which cloud solution you use.