Ask ten people what agentic AI is, and you’ll get eleven different definitions. Some see a digital employee that works autonomously, while others see a glorified chatbot with a few extra buttons. These are two extremes of the spectrum. For us, agentic AI means using AI to automate a step in a process. Nothing more, nothing less. That definition is small enough to start with today, yet broad enough to build on for years to come. Of course, a definition alone isn't the whole story. What is an agent from a technical perspective, what is it good at, and what is it not? This blog explains Quatronics' vision.
Definition: what is an agent?
There are several definitions of agentic AI. Ours—using AI to automate a single step in a process—is intentionally business-focused. It doesn't start with the technology, but with the existing process.
Somewhere in that process is a step that couldn't be fully automated using traditional methods because it required reading, assessing, or articulating something. That is exactly where an AI agent fits in. Think of an incoming email that someone has to review to determine the subject, or a PDF invoice where the line items need to be entered into an ERP system. These aren't strategic tasks; they are isolated steps between two systems where information changes form and where a human was always required. Until now, at least.
The advantage of this definition is that you can precisely quantify the costs or benefits of automation. A single process step always has a measurable metric, such as turnaround time or the number of actions per hour. This makes the conversation with the business much easier than discussing autonomous digital employees.
However, many people view agentic AI as a virtual colleague you give a task to, who then gets to work independently. That is possible, but the most value is often found in automating one time-consuming step rather than an entire process. It is more manageable: the result is measurable, the business case is clear, and implementation takes weeks instead of months.
The image of the digital colleague also has a psychological downside. It creates nervousness among employees ("we're being replaced!") that rarely reflects reality. What the agent does is remove a piece of work that no one enjoyed doing anyway. That should be the framing. Don't start by asking which job an agent can take over, but rather which task employees perform a hundred times a week to the point of boredom.
What an agent can and cannot do
To actually execute a step in a process, you need two things: an AI model—in practice, a (large) language model or LLM—and often an action. That is precisely where the difference from "regular" AI lies.
The model does the thinking: it reads the input, understands what it says, and determines what needs to happen. The action is the concrete step that follows: creating a customer service ticket, updating data, or placing an attachment in a document management system, for example. The AI itself is usually the easy part, while the second side is where the real work lies. Think of permissions, validations, and the question of what should happen if something goes wrong.
What justifies that extra effort? An AI agent excels at three things: interpreting, reasoning, and generating.
Interpreting is extracting meaning from input that is not neatly structured. An email, for example, a free-text field in a form, or a scanned document. The agent determines what it is about and what data the input contains.
Reasoning is about making an assessment within established parameters. Does this fall within the warranty period? Is this an emergency? Is information missing, and if so, what? It is not about creative thinking, but about consistently applying predetermined rules to a situation the agent has not encountered in exactly this way before.
Generating is ultimately about producing output in the format required by the next system or person. A summary, a completed field, a draft response, a structured message, and so on.
If you keep tasks simple and clear, an agent performs them just as well as a human, and often even better. Especially with repetitive or tedious work, humans eventually start making mistakes. An AI agent, on the other hand, maintains the same level of precision on the hundredth request as it did on the first, without any lapse in attention.
However, that comparison only holds true for clear, well-defined tasks. Give an agent an assignment with a vague description and ten exceptions, and it will fail just as miserably as a new intern on their first day. The difference in results rarely lies in the model being used—it is about how clearly and sharply the task is defined.
An agent can get to work anywhere
We can build an agent into all kinds of existing platforms. All of these can call a model, process a decision, and execute an action in another system. That is good news, because it means the platform is almost never the limiting factor.
The real skill lies elsewhere: understanding a process. What exactly happens with which exceptions? Which step takes time? What happens when things go wrong?
If all that is clear, building is simple. If not, regardless of the platform, you will build something that looks good in a demo but requires constant adjustment in production. That is also why we almost always start by putting the process on the table, not the tool.
In both cases, we repeat: write the instructions for the agent as you would for a new employee. Be clear, provide examples, note the exceptions, and state what should happen if something fails. That document is the real construction work. The platform is just where you place it.
A good start is half the battle
Agentic AI isn't about transforming your entire business model. It’s a way to remove steps from a process that no longer belong there. Here are our rules of thumb for getting started.
1. Choose a step, not a job function. Look for a task that happens frequently and is prone to human error. There is your first agent.
2. Keep the scope small. One task, one output, one destination for the result. Multiple agents with smaller assignments are almost always better than one agent with a large one.
3. Match the interface to the process. Use chat for exploration, a portal when a human initiates the task, and no interface at all when the process itself is the trigger.
4. Start with the process flow. Map out the process, solve what can be solved digitally, and assign an agent to the remaining steps.
By following these principles, we deliver something far more valuable than just a digital colleague: a flexible way to handle tasks that no one wanted to do anyway, allowing your real team to focus on the work that truly matters.
Get in touch with
Auke
