Thanks to Snowflake Cortex AI, running a simple database query now allows me to achieve results that, just a few years ago, seemed possible only in science fiction movies.

Dear reader, you probably didn’t expect an answer to the headline question in the very first sentence of this article, did you? Well… I can only apologize for the spoiler. However, I wanted you to realize that instead of struggling with configuration, navigating between interfaces, or building additional dependencies, you can simply sit back and enjoy the results.

How Cortex AI Helps in Customer Opinion Analysis – Case Study

But how does it work in practice? Let me briefly describe a case I recently encountered. I had the opportunity to implement a Cortex AI-based solution that helped quickly contain a reputation crisis spreading across social media.

Imagine millions of customer reviews about your store’s products and services flowing into your cloud data warehouse every hour. Everything runs smoothly until suddenly, a grain of sand clogs the system. Negative reviews start pouring in at an increasing rate. At least, that’s what the social media team claims—and they know what’s happening online. How can you prevent a potential crisis? Simple: you need to find the root cause of customer dissatisfaction.

Fortunately, you have access to all recorded reviews in a structured format within Snowflake. We start by segmenting them into ten categories—ranging from the best to the worst. For this, we use two simple Cortex LLM functions: translate and sentiment. The first one translates the review text into English (let’s be honest, LLM models work best in this language), while the second determines the sentiment of each review on a scale from -1 to 1.

Pretty cool, right? With just a few queries, we can identify which stores had the most dissatisfied customers and determine that, for example, a small group of connected suppliers is responsible for delivering goods to those locations.

Identifying the cause is one thing, but what about solving the problem? Again, Cortex LLM comes to the rescue. The complete function allows us to define issue categories and save them in a separate table. Then, AI can generate, again using complete, a personalized email to the supplier, outlining the identified problems and suggesting solutions. And all of this is based on your own data and the power of LLMs available in Snowflake.

Security and Accessibility – Key Considerations

I hope this simple example sparks your imagination. However, there are two additional critical aspects to consider: data security and accessibility for non-technical users.

Regarding security, it is crucial that your data and its processing results are not shared with other customers, are not used to train external models, and are not provided to third parties. You maintain full control over your data at every stage of processing.

And what about users who are not familiar with SQL or analytical tools? A developer can simply use Streamlit to create a user-friendly application. With Python, they can build a simple program that visualizes customer satisfaction on a scale from 1 to 10 stars, displays the stores with the most negative reviews on a chart, or even automatically generates and sends an email to the supplier with suggested solutions. The user doesn’t even need to know they are interacting with a data warehouse—just a few clicks, and the program, powered by AI, does the rest.

This is just a small glimpse into the possibilities of Cortex AI and Snowflake’s functionalities. And the list of innovative features is long. It’s worth mentioning how easily you can implement chatbots that allow you to query both structured and unstructured data in natural language. Yes, you can even “talk” to your confidential reports stored in PDFs—securely! But I’ll save that for another time… Stay tuned!

The fact is that technologies related to artificial intelligence and machine learning have been around us for several decades and we use them every day without even realizing it. Also companies are outdoing themselves in creating ideas how use AI to build competitive advantage.

Despite the fact that we all use the term artificial intelligence, its definition from the very beginning was hard to precise, and appearing new concepts does not make it easier. So what is the difference between Artificial Intelligence, Machine Learning and Deep Learning? Where can we meet AI in everyday life?

Artificial Intelligence

Artificial intelligence is a broad concept. In general, it aims to imitate human decision-making processes and perform complex tasks in a more human way than ever before. In AI definition you can find construction of machines and algorithms operating with characteristics of human intelligence for e.g.: having the ability to self-adapt to changing conditions. This is a much broader concept than Machine Learning. Behavioral algorithms, virtual agents or autonomously driven self-propelled vehicles are just a few examples of a current application of artificial intelligence.

AI can be divided into two categories:

1. Weak AI (also known as narrow AI) – focuses only on a narrow predefined task, is limited to its scope and does not go beyond
2. Strong AI (also known as general AI) – is a broader concept, in its scope it includes a system with comprehensive knowledge and cognitive abilities, in the assumption similar to human thinking.

Machine Learning

So what is Machine Learning? Machine Learning is a subset of artificial intelligence. Allows the algorithm to grow. The first definition was created by Artur Samuel, who defined the concept of ML in 1959:

 “Field of study that gives computers the ability to learn without being explicitly programmed”.

By analysing huge amounts of data, the system is able to grow and learn how to perform a specific task. Based on an independent analysis, using mathematical algorithms to search data and find models, it is able to predict the result or make a decision. So all machine learning is artificial intelligence, but not all AI is machine learning.

However, machine learning, despite the fact that it is able to develop, when it hasn’t enough data and then faces the necessity of making decisions, human intervention is needed. What if we want to go further?

Deep Learning

Deep Learning is one variation of artificial intelligence that creates multi-layered artificial neural networks that allow a computer to learn and think on its own without the need for direct human intervention. Here we are not dealing with logic based on a linear approach, but with a network of connections that evolves by reorganizing internal connections and creating new ones.

At this point, Deep Learning is being used to improve speech recognition and language processing techniques, among others.

Spotify, Pandora, and Netflix recommend music and movies to you based on past expressed interests and judgments. SIRI when you ask it by voice to check “Where is the nearest gas station?” will help you find useful information. Facebook based on your preferences adds compelling and relevant content to your news feed. What we can be sure of is that artificial intelligence has long been not just futurology. Solutions based on different varieties of this technology have woven themselves into everyday life permanently, and this is just the beginning…