Systems, methods, and devices are provided for determining shape objects to suggest for display on a graphical user interface (GUI). The method may include detecting an input to change one or more objects in an application, in which the object includes an image content, a text content, or both. The method may also include, providing the object to an image classifier, a text classifier, or both in response to detecting the input. Moreover, the method may include receiving a classification of the changed object in response to providing the object. The method may also include identifying suggested shapes for insertion into the application based on the classification. Further, the method may include receiving a request to insert shapes and presenting the suggested shape for insertion in the application.