Automated visual inspection - using cameras and computer vision to spot defects on a production line - had long shown promise, but many manufacturers got stuck after small proof-of-concept projects. On October 21, 2020, Landing AI, the company founded by Andrew Ng (co-founder of Coursera, former chief scientist at Baidu, and founding lead of Google Brain), announced LandingLens to close that gap.
LandingLens is an end-to-end platform that lets manufacturing, quality, and AI teams build, test, deploy, and monitor visual inspection models on the plant floor. In Ng’s framing, it “allows even non-AI experts to train and deploy a model with a few clicks, putting the ownership of the solution in the hands of users.” The company’s pitch reflected Ng’s broader thesis that the bottleneck in industrial AI is high-quality data, not models, so the tooling emphasises capturing labelled examples of good and defective parts rather than hand-building algorithms.
For a general reader, LandingLens is a representative example of how AI vision moved from research demos into routine quality control, and of the “data-centric AI” idea that getting the data right matters more than chasing bigger models.