Think Like an Operator: Building Human Intelligence into Industrial AI

May 5, 2025
How contextualizing plant data and teaching AI to think like seasoned operators can bridge the skills gap and revolutionize decision-making on the shop floor.

Why this article is worth reading:

  • Learn how AI can be trained to emulate the expertise of seasoned plant professionals, bridging the gap left by retiring workers and safeguarding decades of tribal knowledge. 
  • Understand the step-by-step process of contextualizing plant data to enable AI to deliver precise, actionable insights tailored to your operations. 
  • Find out how teaching AI to think like an operator lays the groundwork for agentic AI systems that can proactively investigate, troubleshoot and optimize performance on the plant floor.

If you read my last post, you’ll remember Gary, my nickname for ChatGPT and, unofficially, my extra brain. Gary helps me tackle everything from project documentation to planning vacations. But lately, I’ve been helping Gary understand more about the plant floor. That’s right, I’m teaching Gary. 

You see, more and more people are eager to ask Gary big, important questions like: "Why did Plant A outperform Plant B last month?" 

It's the kind of question that sounds deceptively simple until you realize it’s not. That one prompt packs in countless assumptions, missing context, and requires a level of domain awareness that, for decades, has only existed in the minds of seasoned plant professionals. People who could answer that question without batting an eye. People who are now retiring. 

The good news? AI can help us preserve and scale that knowledge but only if we teach it how to think like a plant person.

From tribal knowledge to AI knowledge

For years, manufacturers have grappled with the so-called "skills gap” with the fear of losing critical operational knowledge as experienced personnel retire. The concern was always real but often felt intangible. Now, however, with the rapid adoption of AI, we’re at a true inflection point. The tools to preserve, structure and scale tribal knowledge finally exist. But it starts with data contextualization.

Large language models (LLMs) are incredible tools for interpreting natural language prompts. But they’re only as smart as the context they’re given. They don’t inherently know how your process works, what your KPIs are, or that “Area 3” means the packaging line on your west campus. We need to train them just like we would a new engineer shadowing operations for six months.

Reverse-engineering human intuition

Let’s go back to the question: Why did Plant A outperform Plant B? 

Before an AI system can even begin to tackle that, we need to take a step back and ask ourselves: How would a human go about answering that?

To do this you need to think about issues such as:

1. What systems would they look at?

  • They might check the historian for throughput data, MES for batch quality, ERP for order completion rates, maybe even LIMS for raw material consistency. 

2. What context do they already know?

  • Plant B just switched to a new raw material supplier.
  • Plant A’s maintenance lead has a strong track record on proactive PMs. * There was a major thunderstorm that impacted Plant B’s power. 

3. How do they phrase things?

  • The CIP never hit temp, so we lost the batch. The extruder was acting up and kept tripping on torque. QA kicked back three pallets for label misalignment. 

This is the human process of data curation and contextualization. We mentally stitch together disparate data, account for anomalies and interpret results based on lived experience. If we can articulate that process, we can begin to teach AI how to mimic it. The data curation blueprint To do this effectively, we must:

  • Map the systems involved: Identify which systems hold relevant information and how they interact (e.g., historian points, MES event records, ERP production schedules). 
  • Standardize semantics: A tank is a tank until it’s also a reactor or a vessel or a unit. Defining a common vocabulary, both machine-readable and human-understandable, is critical. 
  • Capture cause-and-effect relationships: Maintenance events that trigger downtime, raw material lots that impact yield, operator changes that influence performance. These relationships need to be mapped. 
  • Incorporate metadata and domain logic: Not just what happened, but why it mattered in the context of your process. 

When we do this, we aren’t just improving data quality. We’re teaching the AI how to be look at a problem like an operator or a plant manager would.

This is the real work of AI-readiness. Not just spinning up servers or connecting data sources, but building the cognitive map that lets your AI assistant connect the dots like your most trusted shift lead would.

Agentic AI starts with human thinking

Right now, most people are familiar with AI interactions starting with a prompt. You ask, it answers. But the real promise of agentic AI is autonomy, systems that don’t just respond, but proactively investigate, decide and act. To get there, we must do more than feed the AI data. We need to teach it how we think and how experienced operators connect dots, troubleshoot and make decisions based on nuance.

That’s why mapping out the human logic behind questions like “Why did Plant A outperform Plant B?” is so critical. This deeper contextualization isn’t just for better answers, it’s the foundation for AI that can someday act on its own with the judgment of someone who’s walked the plant floor for 20 years.

Contextualization as a competitive advantage

The organizations that will succeed in the next wave of AI adoption are not just the ones with the most data, they will be the ones who can contextualize it best. And that’s where data engineers, integrators, operations professionals and AI practitioners must align. This isn’t just about plugging in a chatbot. It’s about crafting an intentional, strategic approach to mapping your plant’s data landscape, wrapped in the wisdom of your most experienced people. That’s how we turn tribal knowledge into institutional knowledge and give our “industrial Gary” the tools to actually be helpful.

We don’t need AI to replace the plant person. We need it to think like the plant person. That means taking the time to capture, structure and contextualize knowledge in a way that AI can work with. 

This is the real work of AI-readiness. Not just spinning up servers or connecting data sources, but building the cognitive map that lets your AI assistant connect the dots like your most trusted shift lead would. 

Because one day, when someone asks, “Why did Plant A outperform Plant B last month?,” we want the answer to sound less like a guessing game, and more like the confident, data-backed, no-nonsense explanation we’re used to hearing from our veterans. 

Dan Malyszko is vice president at Malisko Engineering, a certified member of the Control System Integrators Association (CSIA). See Malisko Engineering’s profile on the CSIA Industrial Automation Exchange.

Sponsored Recommendations

SEW-EURODRIVE Introduces DR2C motor, IE5 Ultra-Premium Efficiency Motor
Optimize food production with SEW-EURODRIVE’s hygienic, energy-efficient automation and drive solutions for precision, reliability, and sustainability.
George Reed, with the help of Factory Technologies, was looking to further automate the processes at its quarries and make Ignition an organization-wide standard.