Graph Neural Networks (GNNs) are AI models designed to derive insights from unstructured data described by graphs. For different segments and industries, GNNs find suitable applications such as molecular analysis, drug discovery, prediction of developments in stock market, thermodynamics analysis, and even modelling of human brain. Unlike conventional CNNs, GNNs address the challenge of working with data in irregular domains. In this talk, I will provide an introductory overview of the theory behind GNNs, take a closer look at the types of problems that GNNs are well suited for, and discuss several approaches to model unstructured problems as classification or regression at various levels.