The most important attribute for AI storage is performance agility. AI storage must have the ability to grow from a few hundred gigabytes to petabytes, perform well with rapidly changing mixed workloads, serve data to training and production clients simultaneously throughout a project’s life, and support the data models used by project tools. The additional attributes of an ideal AI storage solution are: capacity flexibility, availability and data durability, space and power efficiency, support for data models, security, and operational simplicity.