Skip to content
Practice cases
RetailAdvanced

Stress-Test the Refund Assistant

Build defensible failure chains and define controls before live financial action is enabled.

24 minutes

Scenario

Northstar Retail is piloting an assistant that reads orders, policy and customer messages, then drafts refund amount, reason and destination for agent approval.

Your role
Risk and operations facilitator
Method
Failure Mode and Effects Analysis

Evidence pack

e1

Payment changes

3% of orders contain a changed or replacement payment method.

e2

Policy

Refund rules change monthly and two versions remain searchable.

e3

Interface

The draft highlights amount but not destination account or source passage.

e4

Workload

Agents review up to 65 cases per hour during peak periods.

e5

Model behaviour

Answers remain fluent when no supporting policy passage is retrieved.

e6

Permissions

The pilot is read-only; production design proposes direct payment initiation after approval.

e7

History

Last quarter had four manual wrong-account near misses and no financial loss.

e8

Appeal

Customers can contact support, but no dedicated refund-decision correction route exists.

Constraints

  • Severity ratings must follow the organisation's agreed financial and customer-impact scale.
  • Human review cannot be credited as strong detection without a test of reviewer performance.
  • Residual ratings may change only after controls are implemented and verified.

Case steps

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

1
Open Response

Define two workflow functions and one specific failure mode for each.

2
Structured

For each failure mode, write effect, cause and current prevention and detection controls using e1-e8.

3
Open Response

Prioritise the two chains using severity, occurrence, detection and explicit judgement. Explain any high-severity override of the combined score.

4
Open Response

Define prevention, early detection and safe-recovery actions with owners and verification evidence.