Support Centre

Model Training & Maintenance

Guides on how to create, improve and maintain Models in Re:infer, using platform features such as Discover, Explore and Validation

Understanding Re:infer's data structure and permissions

Within the Re:infer platform, data is structured and stored in a hierarchical manner, which comprises of 3 main components - data sources, datasets and projects. Access to each of these is controlled by strict permissions.


Data Sources


These are collections of raw unlabelled communications data of a similar type, e.g. all emails from a shared mailbox, or a collection of NPS survey responses (see here for more detail). Individual data sources can be associated with an unlimited number of datasets.



These are comprised of 1 - 20 data sources (of similar type with similar intended purposes) and the 'model' that you create when you train Re:infer to understand the data in those sources (see here for more detail).

Projects (formerly Organisations)


A permissioned storage area within the platform. Each dataset and data source belongs to a specific project, which is designated when they are created (see here for more detail). 



These are per-user and specific to each project that a user belongs to. They can provide access to sensitive data and, depending on the permission, allow users to perform a range of different actions in the platform (see here for more detail).



Each dataset and data source is associated with a specific project, with users requiring permissions in those projects to be able to work with the data within them. 


Datasets in one project can be made up of data sources from another project. Users will just require permissions in both projects to view and label the data.


The below illustration helps to illustrate the relationship between these components and permissions:

  • In this example, all of the data sources are associated with Project A, whilst there are datasets associated with both Project A and Project B.
  • If a user wanted to access datasets in Project A (i.e. 1, 2 or 3), they would require viewing permissions for Project A only.
  • But if a user wanted to access datasets in Project B (i.e. 4, 5 or 6), they would require viewing permissions for both Projects A and B, because the data sources are all located in Organisation A.


   Example data structure within Re:infer

Next: Create a Source in the GUI

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.


View all