There is a lot of hype around AI and what it can do for businesses. But it’s important that we are realistic about what AI’s current capabilities are and where it can add the most value. In this post, Artium VP of Engineering John Wilger discusses the current state of AI, its potential in the future, and how businesses can use it effectively. 

How would you describe the current state of AI? What is AI capable of doing today? 

The general public needs to be more aware of what AI can do. Some people fear that AI might take over the world or that AI can solve any conceivable problem. These perspectives are based on misconceptions. We are nowhere close to the idea of a “generalized” artificial intelligence like the ones you see in science fiction, where machines have human-like consciousness and decision-making abilities. 

Generative AI is a tremendous statistical engine. When you input a prompt into a system like ChatGPT, it looks at your input, compares it with a massive dataset, and then makes predictions based on patterns in that data. It feels like you are talking to another human a lot of times. But it's often wrong and can give you some persuasive-sounding incorrect information.

What excites me about AI right now is how it enhances human-computer interaction. I wrote an article about this in Artium’s blog a while ago. An example is how UX patterns are evolving because we can now interact with systems in ways that don’t just involve filling out form fields and clicking buttons. We’re able to teach an LLM about the functions that our software program can perform rather than having to rely on the human user to decide things like “When do I click this button?” or “When do I type into this field?”, the LLM is much better at interpreting the interaction on your behalf. 

I do think we'll find more and more uses in the long term, but that’s one area where AI can make a tangible impact today.

Could you make a few predictions on where you think AI is going to go in the future? 

In the near term, AI will primarily serve as an assistant—one that helps us with tasks we're already familiar with, but in a more efficient way. AI can eliminate much of the manual effort in processing data, connecting disparate systems, and making decisions. However, it will still require human oversight to ensure accuracy and relevance. For instance, businesses might use AI to sift through mountains of data and generate reports, but a human will still need to verify those reports and make critical decisions based on them.

But if we’re looking at the more distant future, that's where things get pretty exciting. Imagine a world where AI isn't just reactive—waiting for us to ask something—but proactive, constantly processing and analyzing incoming data in the background. I envision a future where AI systems can generate insights autonomously without needing a prompt from a human. For example, an AI could monitor real-time sales data and inventory in an e-commerce business and recommend to a business leader, saying, "Based on the trends I'm observing, you should consider marketing Product X this week." That level of proactive decision-making is where I think AI will make a massive leap in the future.

How do you think AI is going to fall short? 

AI’s current limitations remind me of the early days of the internet, especially during the dot-com bubble. Back then, there was an incredible amount of hype around the web, but eventually, that bubble burst. What remained were the foundational pieces that created real value, like the e-commerce platforms we take for granted today.

I think AI will experience something similar. We’re in the middle of an AI bubble, and many people are rushing to use this new technology without fully understanding it. At some point, there will be a “correction,” where the excitement will settle, and we’ll be left with truly valuable applications of AI—those that make our lives easier and our work more efficient.

In the short term, AI will fall short of this Star Trek science fiction dream many have, where it solves all our problems autonomously. But I don't see this as a permanent failure; it's just part of the growth process.

With the rapid advancements in AI, how do you assess the feasibility of solving certain business problems using AI, and how do you manage client expectations about AI’s limitations?

When a client comes to us with a business problem, I first assess whether AI can realistically solve it. The critical question is: “Is this a problem that can be best solved by analyzing data and making connections between facts?” If there’s a pattern in the data, then AI can help. AI is an excellent fit if the problem involves repetitive decision-making or something where historical data can guide predictions—like identifying customer preferences or automating workflows.

But I also make it clear to clients that AI isn’t going to invent solutions out of thin air. It’s not magic. AI might not be the right tool if the problem requires brand-new thinking or if there’s no clear data pattern to draw from. I spend a lot of time managing client expectations, especially given the hype around AI. I explain that AI can be a potent tool, but it’s still a tool. It can help speed up processes and assist in decision-making, but it won’t replace human intuition or creativity. Setting these boundaries helps clients understand what AI can achieve for their business.

Data quality is often cited as a major cause of AI project failure. How do you ensure that your clients have the right data infrastructure and governance in place to support successful AI projects?

Data is fundamental to AI’s success, and many AI projects fail because of poor data quality or infrastructure. Historically, the industry taught software developers to minimize data retention because storage was expensive. We trained developers to build systems that overwrite or delete old data simply because there wasn’t enough room to store everything. But today, storage is cheap, and data has become one of the most valuable assets for any business.

The critical shift that’s happening—and what I emphasize to clients—is the move toward event-sourced systems. Instead of just tracking the current data state, we need to capture the entire sequence of events that lead to a particular outcome. For instance, in an e-commerce setting, don’t just record that a customer bought a product—record every interaction that led up to that purchase. Did they add the item to their cart and then remove it? Did they view the product multiple times before buying? All of these events provide crucial context for understanding customer behavior.

Event-driven data allows AI systems to analyze not only what happened but why it happened. And that’s where AI becomes incredibly powerful. It can connect all those dots and offer far more accurate and meaningful insights. The most important takeaway here is: Don’t lose data. Capture as much as you can because you never know what will be helpful to AI in the future. Storage is cheap, but the value of the data is priceless.