Page 1 of 110
WGU D685 OBJECTIVE ASSESSMENT
(LATEST 2026/2027 UPDATE)
PRACTICAL APPLICATIONS OF
PROMPT ENGINEERING
100% VERIFIED QUESTIONS &
ANSWERS WITH RATIONALES
GRADED A+
HIGH-YIELD REVIEW — 200
QUESTIONS
QUESTION 1
What is the primary goal of prompt engineering in
generative AI?
A) To write longer prompts
B) To maximize the likelihood of a desired model
output
C) To reduce model parameters
D) To train the model from scratch
CORRECT ANSWER: B
RATIONALE: Prompt engineering focuses on
, Page 2 of 110
designing inputs that guide a generative AI model to
produce accurate, relevant, and useful outputs
without modifying the model’s weights.
QUESTION 2
Which of the following is an example of a zero-shot
prompt?
A) "Translate 'Hello' to Spanish." (without
examples)
B) "Here is an example: 'Cat -> Gato'. Now translate
'Dog'."
C) "Classify this sentiment: 'I love this' as positive or
negative after reading 5 examples."
D) "Generate a story based on the following three
examples of fairy tales."
CORRECT ANSWER: A
RATIONALE: Zero-shot means the model receives
no examples; it must rely solely on its pre-trained
knowledge.
, Page 3 of 110
QUESTION 3
In few-shot prompting, what does the "few" refer to?
A) Number of model parameters
B) Number of examples provided in the prompt
C) Number of tokens generated
D) Number of training epochs
CORRECT ANSWER: B
RATIONALE: Few-shot prompting includes a small
number (typically 1–5) of input-output examples to
guide the model.
QUESTION 4
Which technique helps a model reason step-by-step
before giving a final answer?
A) Chain-of-Thought (CoT)
B) Zero-shot classification
C) Temperature adjustment
D) Token truncation
CORRECT ANSWER: A
RATIONALE: Chain-of-Thought prompting
encourages the model to show intermediate
, Page 4 of 110
reasoning steps, improving accuracy on multi-step
problems.
QUESTION 5
What does the "temperature" parameter control in
LLM generation?
A) Length of output
B) Randomness or creativity of outputs
C) Grammar correctness
D) Training data size
CORRECT ANSWER: B
RATIONALE: Lower temperature (e.g., 0.2) makes
outputs more deterministic; higher temperature (e.g.,
0.9) increases randomness and diversity.
QUESTION 6
Setting temperature to 0 typically results in:
A) Highly creative and varied outputs
B) The most deterministic, greedy decoding
C) Random word selection
D) Longer responses
WGU D685 OBJECTIVE ASSESSMENT
(LATEST 2026/2027 UPDATE)
PRACTICAL APPLICATIONS OF
PROMPT ENGINEERING
100% VERIFIED QUESTIONS &
ANSWERS WITH RATIONALES
GRADED A+
HIGH-YIELD REVIEW — 200
QUESTIONS
QUESTION 1
What is the primary goal of prompt engineering in
generative AI?
A) To write longer prompts
B) To maximize the likelihood of a desired model
output
C) To reduce model parameters
D) To train the model from scratch
CORRECT ANSWER: B
RATIONALE: Prompt engineering focuses on
, Page 2 of 110
designing inputs that guide a generative AI model to
produce accurate, relevant, and useful outputs
without modifying the model’s weights.
QUESTION 2
Which of the following is an example of a zero-shot
prompt?
A) "Translate 'Hello' to Spanish." (without
examples)
B) "Here is an example: 'Cat -> Gato'. Now translate
'Dog'."
C) "Classify this sentiment: 'I love this' as positive or
negative after reading 5 examples."
D) "Generate a story based on the following three
examples of fairy tales."
CORRECT ANSWER: A
RATIONALE: Zero-shot means the model receives
no examples; it must rely solely on its pre-trained
knowledge.
, Page 3 of 110
QUESTION 3
In few-shot prompting, what does the "few" refer to?
A) Number of model parameters
B) Number of examples provided in the prompt
C) Number of tokens generated
D) Number of training epochs
CORRECT ANSWER: B
RATIONALE: Few-shot prompting includes a small
number (typically 1–5) of input-output examples to
guide the model.
QUESTION 4
Which technique helps a model reason step-by-step
before giving a final answer?
A) Chain-of-Thought (CoT)
B) Zero-shot classification
C) Temperature adjustment
D) Token truncation
CORRECT ANSWER: A
RATIONALE: Chain-of-Thought prompting
encourages the model to show intermediate
, Page 4 of 110
reasoning steps, improving accuracy on multi-step
problems.
QUESTION 5
What does the "temperature" parameter control in
LLM generation?
A) Length of output
B) Randomness or creativity of outputs
C) Grammar correctness
D) Training data size
CORRECT ANSWER: B
RATIONALE: Lower temperature (e.g., 0.2) makes
outputs more deterministic; higher temperature (e.g.,
0.9) increases randomness and diversity.
QUESTION 6
Setting temperature to 0 typically results in:
A) Highly creative and varied outputs
B) The most deterministic, greedy decoding
C) Random word selection
D) Longer responses
