An AI task is an entity in a broader logical group called a Solution. For example the Solution “Customer Retention”, might include AI tasks of estimating customer satisfaction, customers’ life time value, and customers’ churn risk. You have to create a Solution before creating AI tasks.
We recommend to provide an AI task with a meaningful name such as “Churn Risk Estimation”. An AI task consists of Experiments. Each experiment’s goal is to answer your question with the data and settings you bring. You can run multiple experiments within each AI task – and try to bring different types of data or make different data transformations in order to answer the same question and see which one works best. The first Experiment in your AI task will be created automatically.
After creating an AI task, Wand redirects you to the Training Playground, where you create a data pipeline and train an AI model to use it for predictions. You can create a pipeline in a drag and drop manner by connecting different data sources, transformations, and the Wand ML block, which will perform the ML process end to end.