Module 02 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 most important part of a task definition is…
- A. The backstory
- B. A specific, checkable expected output
- C. The agent name
- D. The tone
2. Elaborate backstories mainly help by…
- A. Improving factual accuracy
- B. Shaping tone and framing - they do not add knowledge or reliability
- C. Reducing cost
- D. Preventing errors
3. Two agents with overlapping roles typically causes…
- A. Redundancy benefits
- B. Duplicated work and contradictory outputs that someone must reconcile
- C. Faster completion
- D. Lower cost
4. A task that says 'research the topic thoroughly' is weak because…
- A. It is short
- B. 'Thoroughly' has no completion criterion, so the agent cannot know when to stop
- C. Research is hard
- D. It needs tools
5. Task context passed between agents should be…
- A. The full transcript
- B. The specific inputs the next task needs, structured
- C. The agent's backstory
- D. Nothing
---
Answer Key and Explanations
Check these only after attempting every question.
1. B - A specific, checkable expected output
Vague expected output is the single largest cause of unusable multi-agent results.
2. B - Shaping tone and framing - they do not add knowledge or reliability
A persona is style guidance. Treating it as capability is a common and costly misunderstanding.
3. B - Duplicated work and contradictory outputs that someone must reconcile
Role boundaries should be as crisp as function signatures.
4. B - 'Thoroughly' has no completion criterion, so the agent cannot know when to stop
Every task needs a definition of done that is observable.
5. B - The specific inputs the next task needs, structured
Dumping everything is expensive and buries the actual instruction.
Practical Check
Apply this module to your own work: complete the module activity for *Roles, Goals, Backstories, and Task Design*, 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.