The automated analysis of microscopic images of microstructures in many cases can benefit from modern artificial intelligence (AI) algorithms. We will present state-of-the-art machine learning integrated in a commercial product making them widely accessible also to non-AI experts, while at the same time also providing an open interface for AI-experts who would like to include in their own machine learning models. By this, powerful AI algorithms can seamlessly be integrated in typical materials analysis workflows where all steps from microscope control, image acquisition over processing and analysis as well as reporting are covered in with one single software. We provide AI tools for several aspects within these workflows: Examples are the AI-based removal of noise from images as a pre-processing step or for easier visual interpretation, the segmentation of objects of interest in an automated image analysis or the classification of identified objects. Our solutions are based on established and well-known tools and formats and are optimized for ease-of-use and integration. They can be employed even in preconfigured workflows for materials analysis such as multiphase or grains analysis. Recently, we further extended the available AI capabilities of our software by also integrating instance segmentation models which yield better segmentation results particularly in the case of touching and/or overlapping objects which we will show on the example of AL Barker etches images.