User:

Log in user:

(step 1 of 2)


Write your email address in the white field and then click the "Confirm" button.

Log in user:

(step 2 of 2)


Write your password in the white field and then click the "Confirm" button.

Log in user - Failure:


Email address has not been found!
Click the "Previous step" button to to enter your email address again.
Or click the "Register user" button to register your email address.

Log in user - Failure:


Pasword doesn't match!
Click the "Previous step" button to enter the password again.

Register user:

(step 1 of 5)


Write your email address in the white field and then click the "Confirm" button.

Register user:

(step 2 of 5)


Registration code has been sent to your email.
Please also check your spam folder.
Copy the registration code from your email into the white field and then click the "Confirm" button.

Register user - Failure:


Email address already exists!
Click the "Previous step" button to enter the email address again.
Or click the "Log in user" button to log in with your email address and password.

Register user:

(step 3 of 5)


Set your user name in the white field and then click the "Confirm" button.

Register user - Failure:


Registration code doesn't match!
Click the "Previous step" button to enter your email address again.

Register user:

(step 4 of 5)


Set your password in the white field and then click the "Confirm" button.

Register user - Failure:


User name already exists!
Click the "Previous step" button to set another user name.

Register user:

(step 5 of 5)


User has been successfully registered.
Click the "Log in user" button to log in.

User settings:

User settings:


Please log in to be able to open user settings.
Click the "Log in user" button to log in with your email address.
Or click the "Register user" button to register your email address.

User settings:


Your subscription has been successfully canceled.

User settings:


Your subscription has been successfully established.

Write comment:

Write your comment in the white field and then click the "Add comment" button.

Let AI do automation projects for you



Robot

When we talk about using AI (artificial intelligence) in programming today, we often focus on individual programming tasks. We let AI write a piece of code. Explain an error. Modify a function. Create a test. Write documentation. All of that is useful.

But I am not thinking about "small" programming tasks here. Maybe we should stop focusing only on how AI can help us with a project and start thinking about how to define the project well enough that AI can do it for us.

This requires a slightly different way of thinking. Instead of: "I do the project. AI helps me." we can gradually move towards: "I define the project so that AI can effectively implement as much of it as possible."

A software department in automation usually does not design the entire machine from scratch. By the time a project reaches a PLC or HMI programmer, much of the information already exists. The process engineering department has defined the technological process and the machine functionality. The electrical engineering department has designed the electrical equipment. There are electrical schematics, pneumatic schematics, hardware, I/O, drives, sensors, valves, and safety components. In addition, there are company standards, existing libraries, coding guidelines, HMI rules, interface definitions, and many other sources of information. The programmer creates the software from this information. In practice, these information sources are often incomplete, inconsistent, or contradictory. A significant part of engineering work is therefore not only translating information into software, but also identifying and resolving these inconsistencies.

Fertile ground for AI:

We cannot simply take a chaotic engineering process, add AI, and expect a miracle.

Project information is often fragmented and not easily accessible. Some of it is in the specification. Some in the electrical schematics. Some in Excel. Some in PDFs. Some in the PLC project. Coding guidelines are somewhere else. Other rules are known only by experienced colleagues. Bringing all of this information together into a consistent and usable form can be a challenge.

Someone who has worked at a company for several years gradually builds up this context. They know where to look, whom to ask, and which information matters. But if we want to hand over a large part of the work to AI, we somehow have to make this context accessible to it.

It is not enough to bring AI into our existing engineering process. We need to prepare the engineering process for AI. AI cannot fix the fact that we do not know what we want ourselves.

We need to know WHAT - what the result should be.

We need to understand WHY - why we need it.

And we need to define or constrain HOW - how the solution should be implemented.

The more knowledge remains only in people's heads or in the company's unwritten practices, the more difficult it is to hand work over to AI.

Engineering work is generally easiest to automate when we understand it well. Ideally, we have already performed it manually several times. Then we know not only the normal workflow. We also know the exceptions, problems, and decision points that may arise along the way. And it is precisely this experience that we need to turn into information and rules that AI can work with.

The more work we want to hand over to AI, the better we need to define what we want. Including things that may seem completely obvious to us. Unclear requirements have always been a problem. AI will not eliminate that problem. On the contrary, it can very quickly produce a large amount of work based on poorly or incompletely defined requirements. Good engineering principles do not become obsolete with AI. They become even more important.

Is our engineering tool ready for AI?

For a long time, engineering tools have been optimized for working with a mouse. It is time to consider both programmatic access and integrated AI capabilities when selecting engineering tools. Tools designed primarily for manual interaction may not be well suited for automated workflows. Do engineering tools provide interfaces that allow AI and other software to work with them directly?

And how do we know the result is correct?

Generated software is not yet a finished project. If we want to hand implementation over to AI, we need to be able to verify that the result actually meets the requirements. The result should be traceable from requirements through architecture and implementation to testing. Where possible, verification should also be independent of the AI process that generated the implementation. AI can support implementation and verification, but responsibility for safety-related decisions remains with the engineering team.

AI also cannot be a one-way production line where we put requirements in at one end and a finished program comes out at the other. During implementation, new questions, problems, and situations will emerge that nobody anticipated during specification. This information needs to flow back to the person who has the authority to decide whether the requirements or the solution need to be changed.

AI is not just a tool for faster programming. If we want to use its full potential, we need to change the way we prepare and implement automation projects. Sometimes, the best way to prepare engineering for AI is not to automate existing structures and workflows, but to replace them with simpler ones designed from the beginning for AI-assisted work. This will allow us to gradually hand over larger parts of the work to AI and make project execution faster and more efficient.

One final note: making company knowledge accessible to AI must also take cybersecurity, confidentiality, and intellectual property requirements into account.

© Radim-Automation, 2020–2026. All rights reserved.
Sharing of this article is permitted with proper attribution (link to the original page).


Related previous articles:


Related next articles: