Computer vision and image analysis research does not easily transition into the commercial landscape due to its research paradigm that it is disconnected from the end users. It is difficult to produce models that account for varying scene and data that occur in real world images and videos. We propose a framework that allow end-users to create custom analytics for their needs. The framework empowers the end-users to create analysis methods that are specific for their tasks, and allows them to inject their data to produce relevant information for better decision making.