In 2019, the JPEG Standardization Committee initiated JPEG AI to define the first image coding specifications, taking advantage of an end-to-end learning-based coding approach. The JPEG AI specifications will be soon published as an international standard in early 2025. JPEG AI exploits the current state of the art in deep learning while taking into account considerations for a deployment in the near future. Therefore, JPEG AI design was refined in several iterations to reach the level of maturity and feasibility to both encode and decode images on mobile devices. JPEG AI offers several benefits when compared to previous conventional coding systems, namely the following: 1) superior rate-distortion performance for perceptual visual quality; 2) much faster coding capability; and 3) the possibility of multipurpose optimization, such as coding for both humans and machines. JPEG AI is based on a learning-based image coding algorithm that can generate a single-stream, compact compressed domain representation, targeting both human visualization, with significant compression efficiency improvement over image coding standards, and effective performance for image processing and computer vision tasks, with the goal of supporting a royalty-free baseline. This article describes how such an objective was achieved in version 1 of the JPEG AI standard by providing technical principles behind its design while giving insights on future steps planned for future extensions of JPEG AI.