The UK company P2i adds water-repelling nanocoatings to smartphones and other gadgets. Normally, it flies engineers to its clients’ factories to identify and solve quality-control problems.

That’s not an option in a world where flights are grounded, borders closed, and security tightened. So in some plants, P2i now relies on a system that uses artificial intelligence to look for even the slightest defects.

“Over the last four months, since the coronavirus, we’ve had to reevaluate how we are going to service and deploy our machines worldwide,” says Neal Harkrider, chief operating officer at P2i.

To spot problems, P2i is using technology from a company called Instrumental. Cameras dotted around P2i’s nano-coating machines examine smartphones after they’ve been treated, and an algorithm sounds an alert if the process appears to have gone awry.

“That vision system is our primary quality-control methodology now,” Harkrider says. He says the company can adjust its tolerance for error on the fly, “and we can do that remotely, which is fantastic.”

The pandemic has forced many manufacturers to rethink established practices. In some places, remote sensing and machine learning substitute for fewer visits, overnight package deliveries, and manual inspections. Robots may be far from displacing humans in manufacturing that requires nimble fingers and flexibility. But systems like the one used by P2i show how AI can help machines carve out niches in manufacturing.

Before Covid-19, Harkrider says, most companies were reluctant to allow outsiders—including their own partners—to connect to their manufacturing equipment, for security reasons. Now, he says, five plants have allowed P2i’s machines, and Instrumental’s inspection technology, to be monitored and controlled remotely.

Bruce Lawler, managing director of the MIT Machine Intelligence for Manufacturing and Operations program, says the pandemic came as manufacturers already were warming to deploying automated inspection technology. “One of the big problems in manufacturing is ‘Where did the problem occur?’” he says. “If you can do more inspection more often, and have a camera on every robot, for every step, then you can say, ‘Well OK, that was here.’”

Manufacturers have long used computer vision to inspect products for defects or other problems, but this traditionally involved hand-coded rules for identifying flaws, making it time-consuming to deploy and change the equipment. Using AI, inspection systems can be fed examples of particular flaws or—as with Instumental’s system—be trained on what a product is supposed to look like and asked to identify abnormalities.