How Classification Works
The AI reads sender, subject, and body, then assigns the most relevant label using:- Sender identity and your relationship
- Email content and whether it requires action
- Label descriptions you define
- Training examples you provide
- Feedback history from past corrections
Default Labels
Most users enable 3-5 labels that match their workflow.
Creating a Custom Label
1
Open Settings
Go to Settings > Labels (
Cmd+,) and click Create Label (or press n l).2
Name and Describe
Give it a name and write a specific description: “Emails from current paying customers about product issues or feature requests. Excludes sales prospects.”
3
Configure
Optionally enable notifications and auto-archive.
Training Examples
The most powerful accuracy tool. In Settings > Labels, click a label and add matched examples (emails that belong) and unmatched examples (emails that don’t). A few well-chosen examples outperform long descriptions.
The Feedback Loop
Every time you move an email between labels, the AI treats it as a correction. Drag the email to the correct tab, or pressl/v to reassign. After a few corrections, the same misclassification rarely recurs.
Per-Label Settings
Related Articles
AI Memories
Teach the AI about your preferences and contacts.
Why Primary Matters
How using Slashy full-time accelerates AI learning.
Inbox Zero Guide
Reach inbox zero using labels and AI.
Inbox Views
Navigate views, filters, and multi-inbox switching.