This page is to brainstorm and coordinate development for better handling email within Tiki using machine learning. This is a great use case, and will serve as an example for integrating machine learning all over Tiki. The Machine Learning is with Rubix ML and the webmail is with Cypht. See also Email as a first-class citizen

Below are some examples. Once we develop the code, they will be easily adaptable to your similar use cases with your data.

Classification use case

  • Emails relevant to bookkeeping (invoices, statements, etc )
  • Emails relevant to servers (server down, monthly uptime report)
  • SPAM or irrelevant emails (Viagra, watch, loto). While mailbox has tools some always pass.
  • Emails that can wait (news, magazines, etc. Nice to read but not essentials to productive work)
  • Email that should be associated to a task, project or client
    • As per Email as a first-class citizen: "Instead of one gigantic mail store, we should have a number of smaller ones that make sense to one's workflow (ex.: around projects, tasks, clients, etc.) and that can easily be shared and prioritized."

Potential workflow

  1. Look at all these folders to train data
    • Past data
  2. When new mail arrives here, here and here
    • If confidence level high, move to relevant folder
    • If confidence level is not high, propose to user and learn from answers

What we want to know

  • Is this an email which requires action (ex.: a bill to pay or a server to tend to) or it's just information that can be analyzed one day if needed.


NextCloud uses Rubix ML as well:

Pablo Duboue