Module 11 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. Your capstone graph must state its autonomy level because…
- A. It is a formality
- B. The controls required depend on whether it suggests, acts with approval, or acts alone
- C. It sets the model
- D. It affects cost
2. The design must name a stop condition, meaning…
- A. A timeout
- B. A defined situation in which the workflow must halt and escalate rather than proceed
- C. An error handler
- D. A token cap
3. Evidence for the capstone should include…
- A. A screenshot
- B. A trace showing state transitions, the approval point, and what was actioned
- C. The source code only
- D. The prompt
4. For a research workflow, the highest-value control is usually…
- A. Faster retrieval
- B. Requiring citations and a review gate before findings are published or actioned
- C. More agents
- D. Longer context
5. An honest capstone write-up includes…
- A. Only successful runs
- B. The failure modes you tested, those you did not, and what remains unverified
- C. Performance numbers only
- D. A launch plan
---
Answer Key and Explanations
Check these only after attempting every question.
1. B - The controls required depend on whether it suggests, acts with approval, or acts alone
Autonomy is the variable that determines how much verification and gating is appropriate.
2. B - A defined situation in which the workflow must halt and escalate rather than proceed
Deciding in advance where the system must not continue is what makes it deployable.
3. B - A trace showing state transitions, the approval point, and what was actioned
A reviewer needs to see the path taken and where the human decision sat, not just the result.
4. B - Requiring citations and a review gate before findings are published or actioned
Research outputs get quoted onward; unverified claims propagate quickly once released.
5. B - The failure modes you tested, those you did not, and what remains unverified
Naming untested territory is what lets a reviewer judge whether the workflow is ready.
Practical Check
Apply this module to your own work: complete the module activity for *Capstone: Approval-Aware Research Workflow*, 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.