Exploring large datasets and identifying meaningful information is still an active topic in many application fields. Dealing with large datasets is currently not only a matter of simply collecting and structuring data for retrieval, but sometimes it also requires the provision of adequate means for guiding the user through the exploration process. Visualizations have shown to be an effective method in this context, the reason being that since they are grounded on visual cognition, people understand them and can naturally perform visual operations such as clustering, filtering and comparing quantities. However, systems which help us to create visualizations often require specific knowledge in data analysis, which ordinary users typically do not possess. To address this gap, we propose a system that guides the user in the data analysis process. To achieve this, the system observes current user behavior, tries to infer the task of the user and recommends the next analysis steps to help her to carry out the task.