Skip to content
Practice cases
Customer ServiceBeginner

Test Support Triage Before Scaling

Design a small PDSA cycle that tests routing value and urgent-case safety before live automation.

18 minutes

Scenario

CloudDesk wants an AI classifier to route incoming support tickets. Leaders want a full launch after a vendor demo.

Your role
Service-improvement lead
Method
PDCA/PDSA Cycle

Evidence pack

e1

Baseline accuracy

Agents correctly route 81% of tickets on first assignment.

e2

Lead time

Median queue-to-agent time is 42 minutes.

e3

Urgent cases

6% of urgent tickets are initially misrouted.

e4

Volume

The service receives 3,000 tickets weekly across twelve categories.

e5

Concentration

Three common categories represent 64% of volume.

e6

Vendor claim

A demo dataset produced 94% overall accuracy; urgent-case sensitivity was not reported.

e7

Review effort

A supervisor can review about 120 predicted labels per hour.

e8

Rollback

The routing engine supports shadow mode and instant return to manual routing.

Constraints

  • The first cycle must not change live routing.
  • Sensitive ticket text must remain in the approved environment.
  • Any later live test must stop if urgent-case performance worsens from baseline.

Case steps

Work through each prompt using the evidence pack. Answers and rubric weights stay protected in the interactive flow.

1
Open Response

Write a measurable aim, baseline and change theory for the first cycle.

2
Structured

Write a prediction and define outcome, process and balancing measures.

3
Open Response

Design the smallest informative Do phase with data, ownership, deviations and safeguards.

4
Open Response

Assume overall accuracy is 92% but urgent-case sensitivity misses the threshold. Study the result and choose the next action.