Training ClickSort on your folders
How ClickSort learns your Outlook folder structure, why its suggestions improve, and how to exclude folders or reset the model.
ClickSort does not ship knowing anything about your mailbox. It learns from the way you file, on your device, and its suggestions get better as it goes.
How the learning works
ClickSort builds a classifier over your own folders. When you file a message it derives features from it — words in the subject, the sender, and similar signals — and records which folder you chose. The next message that looks like it gets that folder as a suggestion.
Three things are worth knowing about how that is built:
- The model is derived, not stored mail. What is kept is counts of features per folder. Subjects, bodies, recipients and attachment names are used in memory to derive those counts and then discarded.
- It lives on your device, in the add-in's browser storage inside your Microsoft 365 session, partitioned per tenant and mailbox. It is not uploaded, and there is no server-side classifier.
- There is no LLM anywhere in the filing path. Suggestions come from a small statistical model that runs locally, which is why they are instant and why nothing has to be sent anywhere to produce them.
Getting good suggestions faster
- File the way you actually want to file. Every file is a training example, including the ones where you override the suggestion. Correcting a wrong suggestion is the most useful thing you can do.
- Give a folder a handful of examples before expecting it. A folder you have filed into once is not yet a pattern.
- Keep the folder you file to specific. ClickSort learns the distinction you make; if two folders hold the same kind of mail, no model can tell them apart.
Excluding folders
Folders you never file to by hand — archives, shared clutter, system folders — can be excluded, so they stay out of suggestions and out of search. Excluded folders and onboarding state are stored with the model, on your device.
Resetting the model
Clearing the add-in's stored data resets the model to nothing: the learned counts, the folder cache and your preferences all go, and ClickSort starts over from the next file. Removing the add-in has the same effect. Nothing needs to be deleted from a Vonian server, because nothing was ever there.
The cached list of your folders refreshes when it is more than a day old, and is replaced rather than accumulated.
Related
- Filing an email — the action the model learns from
- Data and privacy — exactly what is held, where