Cambrian LabEvolve my prompt
← All case studies
📝
Species: Sorter · Gen 1.0

Customer Review Categorizer

Triage inbound reviews automatically

Classify reviews as COMPLAINT, FEATURE_REQUEST, PRAISE, SUPPORT_ISSUE, or BUG_REPORT. Route to the right team.

Primary use cases
  • G2 / Trustpilot aggregation
  • App Store review routing
  • Product feedback triage
Run this on your prompt →Try the classifier live
Why you can’t just prompt-engineer this yourself

The evolution story

Sorter was trained on the ambiguous boundaries reviewers cross (complaints that sound like bugs, praise that hides feature requests). 96% accuracy on unseen reviews.

Live demo

Try Sorter — Gen 1.0

0/8000 characters

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

Evolutionary lineage

Sorter is a Gen 1.0 agent

1.0
Generation 1.02026-04-14

Initial release. 96% accuracy on 50-sample validation pool.

Measured accuracy: 96%

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 Sorter. First evolution is free.

Evolve my prompt →