Module 10 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. The scope must state the autonomy level because…
- A. it sounds rigorous
- B. the controls you have to build follow from whether it suggests, acts with approval, or acts alone
- C. reviewers ask for it
- D. it affects cost
2. Which actions get a gate?
- A. all of them
- B. the irreversible ones, and the gate goes immediately before the first
- C. the expensive ones
- D. whichever the reviewer requests
3. Stopping ceilings should be sized from…
- A. the typical run
- B. the worst legitimate run
- C. the fastest run
- D. the provider's rate limit
4. Which case can manual testing structurally not produce?
- A. a missing input
- B. a duplicate resume after approval
- C. an over-limit amount
- D. an unregistered tool
5. A risk review with no untested areas listed…
- A. indicates thorough work
- B. reads to an experienced reviewer as an analysis that was not done
- C. is the goal
- D. is required for sign-off
---
Answer Key and Explanations
Check these only after attempting every question.
1. B - the controls you have to build follow from whether it suggests, acts with approval, or acts alone
It also sets the window between a wrong action and anyone noticing.
2. B - the irreversible ones, and the gate goes immediately before the first
Gating everything produces approval fatigue, and by the third gate every request is approved reflexively.
3. B - the worst legitimate run
Sized from the typical run you spend the next month raising them, and eventually stop trusting them.
4. B - a duplicate resume after approval
A person clicking through does each thing once, so the second resume never happens in any hand-run test.
5. B - reads to an experienced reviewer as an analysis that was not done
They know the gaps exist, so a list of none means they now have to find them without your knowledge of the system.
Practical Check
Apply this module to your own work: complete the module activity for *Capstone: Agent Workflow Design and Risk Review*, 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.