Classification Signals
When AI is turned on, MailPrism reads each email and produces a set of signals. This page explains every signal, the values it can take, and what each value means. All of these are available as rule conditions.
These signals only exist when AI features are enabled. See AI, Explained and AI privacy & consent.
Category
The category is MailPrism's best guess at what kind of email this is. These are the built-in categories:
urgent important personal work financial newsletter promotional cold_email spam social notification transactional system| Category | Meaning |
|---|---|
| urgent | Needs your attention right now |
| important | High-priority, but not time-critical |
| personal | From friends, family, or your personal life |
| work | Job- or project-related |
| financial | Invoices, billing, receipts, statements |
| newsletter | Subscriptions and recurring digests |
| promotional | Marketing, sales, and offers |
| cold_email | Unsolicited outreach you didn't ask for |
| spam | Unwanted or junk mail |
| social | Notifications from social networks |
| notification | Automated alerts from apps and services |
| transactional | Order confirmations, shipping, account actions |
| system | System-generated mail (e.g. delivery reports) |
Categories aren't fixed. On Pro and above you can create custom categories and even edit the built-in ones. See Custom categories.
Urgency
How time-sensitive the email is.
| Value | Meaning |
|---|---|
| high | Act soon |
| medium | Worth attention, not pressing |
| low | No rush |
Sentiment
The emotional tone the AI reads in the message.
| Value | Meaning |
|---|---|
| positive | Friendly, appreciative, upbeat |
| neutral | Matter-of-fact |
| negative | Frustrated, unhappy, or critical |
Great for spotting an unhappy customer before it escalates.
Yes / No signals
These are simple true/false flags. Each is usable as a rule condition with an is true / is false operator.
| Signal | Means it's true when… |
|---|---|
| Is spam | The email looks like junk or unwanted mail |
| Is automated | The email is machine-generated with no human sender (receipts, notifications, system alerts) |
| Is cold outreach | The email is an unsolicited sales pitch or cold outreach |
| Needs response (detected) | The email looks like it needs a reply from you |
| Requires action (detected) | The email needs an action outside email — sign in, approve, update payment, etc. |
| Sender expects reply (detected) | The sender appears to be waiting on a response from you |
An email can't be both "cold outreach" and "needs a response" at the same time — by design, flagging something as cold outreach keeps it out of your needs-action queue.
The last three signals — needs response, requires action, and expects reply — also feed response tracking, which decides a whole thread's state rather than judging a single message.
Confidence
Every classification carries a confidence score from 0.0 to 1.0 — how sure the
AI is about its answer. You can use this to keep automations conservative:
If Category is
cold_emailand confidence is greater than0.8, archive it.
Two related, optional values may also be present:
- Alternative category — the AI's runner-up guess, when it was torn between two.
- Category confidence — confidence specific to the category choice.
For anything destructive (archive, delete, forward), pair an AI signal with a concrete condition like sender relationship, and require high confidence. See Best practices.
Where these appear
| Signal | As a rule condition |
|---|---|
| Category | AI Category |
| Urgency | AI Urgency |
| Sentiment | AI Sentiment |
| Is spam | AI: Is Spam |
| Is automated | AI: Is Automated Email |
| Is cold outreach | AI: Is Cold Outreach |
| Needs response | AI: Email Needs Response |
| Requires action | AI: Requires External Action |
| Sender expects reply | AI: Sender Expects Reply |
| Thread state confidence | AI: Thread State Confidence |
See the full Conditions reference.
→ Next: Custom categories · Smart rules