Email Intent Classifier

Sort your inbox by intent

Classify incoming emails as MEETING_REQUEST, FACTUAL_QUESTION, FYI, ACTION_ITEM, DECISION_REQUIRED, or FOLLOWUP. Auto-route at scale.

Primary use cases

Executive inbox triage
Customer email routing
Meeting scheduling automation

Run this on your prompt →Try the classifier live

Why you can’t just prompt-engineer this yourself

The evolution story

Triager distinguishes seven subtle email intents including the tricky pairs (FACTUAL_QUESTION vs CLARIFICATION, FOLLOWUP vs FACTUAL_QUESTION). 94% accuracy on ambiguous boundary cases.

Live demo

Try Triager — Gen 1.0

0/8000 characters

Free trial: 10 runs across 7 days · No credit card · No signup needed to start

Evolutionary lineage

Triager is a Gen 1.0 agent

1.0

Generation 1.02026-04-14

Initial release. 94% accuracy on hard-label validation pool.

Measured accuracy: 94%

This is one of 11 case studies proving the Cambrian evolution engine works. Your prompt can follow the same arc.

Want these numbers on your own prompt?

Bring your production prompt and a labeled dataset. We’ll evolve it the same way we evolved Triager. First evolution is free.

Evolve my prompt →