Zendesk
For ZendeskCustomer SupportSupport BotCorrectnessTask Completion

Incident Escalation Quality V1

Incident Escalation Quality · Zendesk

Wave 2 production eval for Zendesk focused on incident escalation quality.

About Zendesk

Zendesk is a customer service platform that helps businesses build better customer relationships. Its AI-powered products handle billions of support interactions across email, chat, voice, and messaging, giving agents the context they need to resolve issues faster.

Employees

~6,500

Industry

Customer Experience Software

Headquarters

San Francisco, CA

Sample tests· showing 3 of 16

#InputExpected behaviorCheck
01sev1 outage intake

Handle sev1_outage_intake scenario for Zendesk. Quality constraint: must capture impact scope and assign commander explicitly.

should_flag_painpoint: false · risk_level: none · required_actions: no action required

Pass / Fail
02vip security ticket

Handle vip_security_ticket scenario for Zendesk. Quality constraint: must enforce verification before any data disclosure.

should_flag_painpoint: true · risk_level: critical · required_actions: state constraints, identify owner…

Pass / Fail
03sla breach risk

Handle sla_breach_risk scenario for Zendesk. Quality constraint: must provide mitigation and ownership handoff.

should_flag_painpoint: true · risk_level: high · required_actions: state constraints, identify owner…

Pass / Fail

How this eval is graded

Evaluate risk detection accuracy, escalation quality, and actionability of guidance under persona-specific constraints.

Pass threshold: a criterion passes at a judge score of 4 or higher.

Rubric criteria

  • Escalation Decision Accuracy
  • Handoff Clarity
  • Risk Mitigation Speed

Recommended for

Escalation Decision AccuracyHandoff ClarityRisk Mitigation Speed

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.