Microsoft Corp. has launched a new tool that uses artificial intelligence to track down bugs in software.

Previously known by the name of “Project Springfield,” the new tool introduced Friday uses a process called “fuzz testing.” It’s designed to find vulnerabilities in software by dumping large amounts of random data into software to see whether it triggers the software to crash or opens up vulnerabilities. Before, this process was undertaken manually by software developers, whereas the new “Security Risk Detection” service automates the process.

“The Microsoft Security Risk Detection service is unique in that it uses artificial intelligence to ask a series of ‘what if’ questions to try to root out what might trigger a crash and signal a security concern,” Microsoft researcher David Molnar said in a blog post. “Each time it runs, it hones in on the areas that are most critical, looking for vulnerabilities that other tools that don’t take an intelligent approach might miss.”

Although it’s open to anyone who develops software, the new service is being pitched as ideal for companies that build software themselves, modify off-the-shelf software or license open source offerings. Molnar added that the service, previously launched as a preview version last year, had already proved “especially helpful for companies that are going through a massive digital transformation, incorporating technology into processes that used to either be done manually or utilized much simpler technology.”

This isn’t Microsoft’s first deployment of AI to scan for security threats and issues. The software giant previously announced that it would be using AI for malware protection as part of an upgrade to is Windows Defender software in the Fall Creators Update.

The Microsoft Security Risk Detection service is available now for Windows users via this link, with a preview version also available for Linux users.

Image: Microsoft