A multi-tenant, cloud-based Software-as-a-Service (SaaS) manufacturing cloud system offers a variety of industrial applications to end customers, including but not limited to MES, ERP, quality management, supply chain management, and customer relationship management (CRM). The system includes extensibility tools that allows industrial customers to customize databases, data collection templates, reporting fields, and other features of their consumed services, eliminating the need for these features to be customized by an administrator of the cloud system. Some embodiments of the manufacturing cloud system can also leverage generative artificial intelligence (AI) in connection with executing its supported services.

In certain aspects of the disclosure, a computer-implemented method includes receiving a selection of a model from a plurality of models running on an ecosystem. The method includes receiving annotated datasets with correct examples and incorrect examples. The method includes training, responsive to receiving the annotated datasets, the model based on the annotated datasets. The method includes running the model based on the training. The method includes receiving a feedback score of results from running the model based on the annotated datasets. The method includes iteratively running, until the feedback score is above a predetermined threshold, the model responsive to user evaluation of the results from running the model based on the annotated datasets. The method includes publishing the model responsive to the feedback score being above the predetermined threshold.

In certain aspects of the disclosure, a computer-implemented method includes receiving a selection of a model from a plurality of models running on an ecosystem. The method includes receiving annotated datasets with correct examples and incorrect examples. The method includes training, responsive to receiving the annotated datasets, the model based on the annotated datasets. The method includes running the model based on the training. The method includes receiving a feedback score of results from running the model based on the annotated datasets. The method includes iteratively running, until the feedback score is above a predetermined threshold, the model responsive to user evaluation of the results from running the model based on the annotated datasets. The method includes publishing the model responsive to the feedback score being above the predetermined threshold.