# Gather ### C**reate an upload batch** A batch is a group of documents that you will upload at the same time. You can name the batch or keep the id that will be automatically be created.

### **Upload files to the batch** Select the desired files for the batch and start extracting the data by clicking in Process Files

### **Review the extracted data** Once the data is extracted, each datapoint will have one of three statuses: Ready, Need Review, or Rejected. If the AI successfully finds the data it was looking for, it will be marked as Ready for you to save. If something seems wrong, you will need to review it and edit any fields that might be missing or where the data doesn't seem right. If the file is corrupted or unsupported for any reason, it will be marked as Rejected.

## **Creating a data point** After reviewing all your files, you can save them in the platform as validated data points. There are two options available: involving a human in the loop to validate all the collected information, or creating a Data Point directly for the given information. Creating a Data Point guarantees that the original document and the structured information are linked and stored on the Cedalio platform, with every change to this data point being tracked. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.cedalio.com/studio/gather.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.