AI Assists Mendix Low-Code Tool for Enterprise Mobile, Web Apps
Low-code tool vendor Mendix today claimed the first artificial intelligence-assisted offering for quickly creating enterprise mobile and Web apps.
Specifically, Mendix announced Mendix Assist for its low-code application development platform, leveraging machine learning.
Machine learning is put to use in the analysis of more than 5 million anonymous application flows culled from apps built with the Mendix platform, providing next-step suggestions in the developer workflow. These suggestions can provide the correct next developer step with 90 percent accuracy, the company said.
This reportedly can improve enterprise app development in three main ways: boosting developer productivity; mentoring new developers; and decreasing the cost and time impact of defects.
Mendix said the continuous machine learning functionality also improves the tool during use, making it "smarter" over time by learning algorithms to boost the AI knowledge base and leverage insights gleaned from all Mendix app usage. This can help customize functionality to suit an organization's business processes and development style, it said.
"We use machine learning to detect best practice patterns in microflows," the company said in a blog post today. "Based on this we can now assist developers when building a microflow by suggesting the most sensible next step they can take. This suggestion is based on the previous activities and the context of a microflow. We tested Mendix Assist on existing models and saw that it predicts the next activity in a microflow correctly in 90 percent of the cases."
The company's Jeff Goldberg demonstrated how Mendix Assist can help build microflow logic to recalculate a total order amount for an order management application in a YouTube video.
The company plans on shipping the first version of Mendix Assist in the third quarter of this year.
David Ramel is the editor of Visual Studio Magazine.