Module 01 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. What single property distinguishes an agent from a script?
- A. It calls a language model
- B. Its next step is decided during the run rather than written in advance
- C. It uses tools
- D. It runs without supervision
2. A workflow classifies a ticket and routes it to one of four fixed queues. This is…
- A. an agent, because a model decides
- B. a script - the destinations and the rule both exist before the run
- C. an agent, because different tickets go different ways
- D. neither
3. As autonomy rises, the cost that grows fastest is…
- A. token spend
- B. the window between a wrong action and anyone noticing
- C. latency
- D. the number of tools required
4. The most useful question to ask of a vendor demo is…
- A. how many tools does it use?
- B. was that input chosen or typical?
- C. which model is it?
- D. how fast was it?
5. You should move up from a script to an agent when…
- A. the task feels complex
- B. a named requirement forces it - a run-time-dependent sequence, a pause, or surviving interruption
- C. the task involves AI
- D. there are several steps
---
Answer Key and Explanations
Check these only after attempting every question.
1. B - Its next step is decided during the run rather than written in advance
Control flow, not technology. A scripted workflow with four model calls is still a script.
2. B - a script - the destinations and the rule both exist before the run
The sequence does not depend on anything computed during the run; only which of four known branches is taken.
3. B - the window between a wrong action and anyone noticing
At the lowest level a human performs the action, so a wrong suggestion is caught immediately. At the highest, you learn from the consequence.
4. B - was that input chosen or typical?
Everything else is downstream. A curated input tells you the system handles that input, which was never in doubt.
5. B - a named requirement forces it - a run-time-dependent sequence, a pause, or surviving interruption
Each row up the list adds machinery that can fail. Name the requirement or the simpler structure was sufficient.
Practical Check
Apply this module to your own work: complete the module activity for *What an Agent Is and What It Is Not*, 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.