MACHINE-LEARNING

Email Intent Classifier Confusion Matrix

An email-intent classifier sends customer messages to Order, Return, Shipping or Account queues. The matrix shows correct assignments on its diagonal and the cross-queue errors around it. For example, Return messages sent to Order may indicate ambiguous wording or an unclear intent definition. This view helps an automation team decide where human review remains necessary. It should be refreshed after policy changes or new product launches because the language customers use can change. The values are counts, not percentages, so reviewers should also consider the total volume for each row before declaring one class better than another.

UPDATED 2026-09-25
EXAMPLEEmail Intent Classifier Confusion Matrix
Make this diagram your own.

Open it in the AI editor with a prompt pre-filled — keep what works, change what doesn't.

CASE ANALYSIS

Scenario

An automation team checks routing errors before enabling email triage.

Key decisions

  • Use customer intents: Align classes with real queues.
  • Review related intents: Order and Return errors may need new examples.
  • Track validation date: Compare the same test protocol over time.

When to reuse this

Use when one incoming email has one agreed routing intent.

FAQ

Frequently asked questions

Why include four intents?01
It reflects distinct queues in a common support-routing workflow.
What does an off-diagonal count mean?02
It is a message routed to a different intent from its actual label.
Should this run without review?03
That depends on the impact of each routing error and the team's controls.
Open this example in the editor →

Tweak it with chat, export PNG/SVG, or fork it for your own use case.