Machine learning and CAD UX. What happens when you run out of space for your CAD toolbar buttons?

Machine learning and CAD UX. What happens when you run out of space for your CAD toolbar buttons?

User interface or how we more often call it these days “user experience” (UX) is tough. Enterprise systems, PLM and CAD systems are not the easiest technologies in the world. I wrote many articles in the past discussing how important simple and intuitive user interface. Check my articles here. But it is hard to do.

Everyone who ever touched the CAD interface is familiar with the user interface paradigm. Buttons, buttons, buttons… Tons of toolbars with buttons. This is how it was for decades long in Microsoft Windows user interface, but not only.

A long time ago, CAD systems used tablets with command interface, but these days you can only find them in a museum of computers (I’ve seen one in Palo Alto, CAD a few years ago). AutoCAD and some other systems had a command line user interface, which was brilliant back in 1990s, but I’m not sure how many people still like it. But I digressed…

What to do if you run out of space for toolbars and buttons? And what to do, if the amount of buttons is so much confusion that it makes very hard to work.

Siemens NX is coming with a new thing called “New adaptive UI”. Fancy name- kudos to Siemens PLM marketing department. It also ties to a very much trending technology such as machine learning and artificial intelligence. Check this article. Here is the passage:

Think of the adaptive UI as your personalized assistant that will help optimize workflows and increase productivity for every single user within your organization. The adaptive UI will predict the commands that you will most likely want to use based upon the context of what you’re doing at the moment. It will put these recommended commands in a clean and compact panel to speed you through your workflow. The panel will reflect differently based upon each users unique style of usage in NX. Experienced users of NX can even share their workflows with the rest of the organization to help promote best practices. Used effectively, this can speed the entire organizations productivity.


Chad Jackson of Lifecycle Insights explains the same technology in a “normal English” with less marketing. Check it out.


Siemens PLM work reminded me of some of the technologies introduced by Gmail last year – automatic email phrase completion. Check this article.

What is my conclusion? The use of machine learning in recognition of commands and placing correct commands in front of the user is a very good idea and I can see it widely adopted in the future. But… to make it useful, CAD companies will need to learn how to bring relevant data and make it work. When it works, it can be great. You want it to be right in 90% of situations, otherwise, it can be annoying. So, details matter. Also, will be interesting what other CAD vendors will do. Cloud CAD and PLM companies might be one step closer to the efficient realization of machine learning since the date is much easier access for analysis. Just my thoughts…

Best, Oleg

Disclaimer: I’m co-founder and CEO of OpenBOM developing cloud based bill of materials and inventory management tool for manufacturing companies, hardware startups and supply chain. My opinion can be unintentionally biased.


Share This Post