Module 09 Knowledge Check
5 questions. Pass mark 4 out of 5. Answer every question before checking the answer key below, then retry after reading the feedback.
1. A workflow with adequate volume whose cases all differ is…
- A. an ideal candidate
- B. a poor candidate - the judgement is the work
- C. suitable if you add more rules
- D. suitable at any volume
2. An approval chain with a two-to-five day latency requires…
- A. a longer timeout
- B. durable state, because nothing can be held open that long
- C. a faster model
- D. more reviewers
3. Triage rules should be run over real historical records because…
- A. it is faster
- B. the exception rate decides whether the automation is worth building
- C. it trains the model
- D. auditors require it
4. An honest comparison against the manual process must include…
- A. hours saved only
- B. review time and both error rates
- C. token cost only
- D. the number of steps automated
5. Remaining manual work after automation is…
- A. a defect to be eliminated
- B. a finished design, if the boundary is stated with its reason
- C. a sign the tool is wrong
- D. always temporary
---
Answer Key and Explanations
Check these only after attempting every question.
1. B - a poor candidate - the judgement is the work
Automate the routine slice and route the exceptions to a person deliberately.
2. B - durable state, because nothing can be held open that long
The run has to survive being put down and picked up by a different process.
3. B - the exception rate decides whether the automation is worth building
If 40% are exceptions, the value is much smaller than the proposal assumed - better to know before building.
4. B - review time and both error rates
Review time usually dominates the automated column, and the error rate often goes up.
5. B - a finished design, if the boundary is stated with its reason
An automation that quietly attempts everything fails unpredictably on the cases nobody chose to include.
Practical Check
Apply this module to your own work: complete the module activity for *Designing Workplace Automations Safely*, then write one sentence naming what your result shows and one naming what it does not.
Strong Answer Pattern
A strong answer names the task, the evidence used, the check performed, and the remaining limitation. It avoids "proved", "guaranteed", or "always" unless the evidence genuinely supports it.