CX Agent Eval Reports

Explore how agents handle specific support workflows, including Shopify and retail. Each report covers its own task set, findings, and supporting evidence.

Yuma

Retail customer support

Yuma customer support evaluation

Results from 50 retail support tasks, with exchanges, returns, and an order change behind the scores.

Evaluated November 5, 2026

Read full report

Gorgias

Shopify customer support

Gorgias customer support evaluation

A closer look at task outcomes, policy adherence, and three conversations behind the scores.

Evaluated October 13, 2026

Read full report

Zendesk

Customer support

Zendesk customer support evaluation

Task performance, response quality, and supporting cases.

Evaluated October 12, 2026

Request access

Forethought

Customer support

Forethought customer support evaluation

Task performance, response quality, and supporting cases.

Evaluated October 18, 2026

Request access