WGU D685 EXAM
WGU D685: Practical Applications of Prompt
Engineering — Objective Assessment 2
Comprehensive 200-Question Practice Exam with
Detailed Answer Rationales, Scenario-Based Case
Studies, and Domain-Specific Competency
Coverage for the 2025/2026 Objective Assessment
================================================================================
WGU D685: PRACTICAL APPLICATIONS OF PROMPT ENGINEERING
OBJECTIVE ASSESSMENT 2 — COMPREHENSIVE EXAM
================================================================================
EXAM TITLE: WGU D685 Practical Applications of Prompt Engineering
Objective Assessment 2 — Comprehensive 200-Question Practice Exam
VERSION: 2026/2027 Objective Assessment Preparation Edition
TOTAL QUESTIONS: 200
QUESTION FORMAT: Multiple-Choice, Select-All-That-Apply, True/False,
Scenario-Based, and Case Study Questions
TIME ALLOTTED: 180 Minutes (Recommended)
PASSING STANDARD: Competency-Based (Recommended 80% or Higher)
--------------------------------------------------------------------------------
EXAM DOMAINS COVERED
--------------------------------------------------------------------------------
pg. 1
, WGU D685 EXAM
1. Foundational Theories of Prompt Engineering
2. Advanced Prompt Crafting and Optimization Techniques
3. AI Model Capabilities, Limitations, and Hallucination Management
4. Ethical AI, Bias Detection, and Responsible Prompt Design
5. Legal and Regulatory Compliance (GDPR, CCPA, EU AI Act)
6. Professional Standards and Best Practices in AI Interaction
7. Scenario-Based Problem Solving and Critical Decision-Making
8. Security and Privacy in Prompt Engineering
--------------------------------------------------------------------------------
INSTRUCTIONS TO CANDIDATES
--------------------------------------------------------------------------------
1. Read each question carefully before selecting your answer.
2. Each question has one or more correct answers as indicated.
3. Do not reveal or review the answer key until the exam is complete.
4. Answer rationales are provided immediately following each question for
study and self-assessment purposes.
5. Maintain academic integrity at all times.
================================================================================
BEGIN EXAMINATION
================================================================================
pg. 2
, WGU D685 EXAM
WGU D685: Practical Applications of Prompt Engineering
Objective Assessment 2 — Comprehensive Exam
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 without modifying model weights
C. To reduce model parameters
D. To train the model from scratch
ANSWER:
B. To maximize the likelihood of a desired model output without modifying model weights
RATIONALE:
Prompt engineering focuses on designing inputs that guide a generative AI model to produce
accurate, relevant, and useful outputs without modifying the model's weights. The goal is to elicit
the best possible response through careful input design, not to alter the underlying model
architecture or training .
QUESTION 2:
Which of the following is an example of a zero-shot prompt?
A. "Here is an example: 'Cat → Gato'. Now translate 'Dog'."
B. "Translate 'Hello' to Spanish." (without examples)
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."
ANSWER:
B. "Translate 'Hello' to Spanish." (without examples)
RATIONALE:
Zero-shot prompting means the model receives no examples and must rely solely on its pre-trained
knowledge. Option A is an example of one-shot prompting (one example provided), Option C is few-
shot prompting (5 examples), and Option D is few-shot prompting (3 examples) .
QUESTION 3:
What does the "temperature" parameter control in LLM generation?
A. Length of output
B. Grammar correctness
C. Randomness or creativity of outputs
D. Training data size
ANSWER:
C. Randomness or creativity of outputs
pg. 3
, WGU D685 EXAM
RATIONALE:
Temperature is a sampling parameter that controls the probability distribution of token selection.
Lower temperature (e.g., 0.2) makes outputs more deterministic and predictable; higher
temperature (e.g., 0.9) increases randomness, diversity, and creativity .
QUESTION 4:
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
ANSWER:
B. The most deterministic, greedy decoding
RATIONALE:
At temperature 0, the model always selects the token with the highest probability at each step,
producing deterministic outputs. The same prompt will generate the same (or very similar) response
each time, making this setting ideal for tasks requiring consistency and factual accuracy .
QUESTION 5:
What is the purpose of the "top_p" (nucleus sampling) parameter?
A. Limit the number of tokens generated
B. Choose from the smallest set of tokens whose cumulative probability exceeds p
C. Adjust grammar style
D. Increase prompt length
ANSWER:
B. Choose from the smallest set of tokens whose cumulative probability exceeds p
RATIONALE:
Top-p (nucleus sampling) dynamically selects the smallest set of words whose cumulative probability
exceeds a threshold (p). For example, top-p=0.9 selects the set of words that cumulatively represent
90% of the probability mass, creating more diverse and coherent outputs than top-k sampling in
many cases .
QUESTION 6:
A user writes, "You are a high school math teacher. Explain the Pythagorean theorem." Which
prompt component is "You are a high school math teacher"?
A. Constraint
B. Format specification
C. Persona assignment
D. Output length specification
pg. 4
WGU D685: Practical Applications of Prompt
Engineering — Objective Assessment 2
Comprehensive 200-Question Practice Exam with
Detailed Answer Rationales, Scenario-Based Case
Studies, and Domain-Specific Competency
Coverage for the 2025/2026 Objective Assessment
================================================================================
WGU D685: PRACTICAL APPLICATIONS OF PROMPT ENGINEERING
OBJECTIVE ASSESSMENT 2 — COMPREHENSIVE EXAM
================================================================================
EXAM TITLE: WGU D685 Practical Applications of Prompt Engineering
Objective Assessment 2 — Comprehensive 200-Question Practice Exam
VERSION: 2026/2027 Objective Assessment Preparation Edition
TOTAL QUESTIONS: 200
QUESTION FORMAT: Multiple-Choice, Select-All-That-Apply, True/False,
Scenario-Based, and Case Study Questions
TIME ALLOTTED: 180 Minutes (Recommended)
PASSING STANDARD: Competency-Based (Recommended 80% or Higher)
--------------------------------------------------------------------------------
EXAM DOMAINS COVERED
--------------------------------------------------------------------------------
pg. 1
, WGU D685 EXAM
1. Foundational Theories of Prompt Engineering
2. Advanced Prompt Crafting and Optimization Techniques
3. AI Model Capabilities, Limitations, and Hallucination Management
4. Ethical AI, Bias Detection, and Responsible Prompt Design
5. Legal and Regulatory Compliance (GDPR, CCPA, EU AI Act)
6. Professional Standards and Best Practices in AI Interaction
7. Scenario-Based Problem Solving and Critical Decision-Making
8. Security and Privacy in Prompt Engineering
--------------------------------------------------------------------------------
INSTRUCTIONS TO CANDIDATES
--------------------------------------------------------------------------------
1. Read each question carefully before selecting your answer.
2. Each question has one or more correct answers as indicated.
3. Do not reveal or review the answer key until the exam is complete.
4. Answer rationales are provided immediately following each question for
study and self-assessment purposes.
5. Maintain academic integrity at all times.
================================================================================
BEGIN EXAMINATION
================================================================================
pg. 2
, WGU D685 EXAM
WGU D685: Practical Applications of Prompt Engineering
Objective Assessment 2 — Comprehensive Exam
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 without modifying model weights
C. To reduce model parameters
D. To train the model from scratch
ANSWER:
B. To maximize the likelihood of a desired model output without modifying model weights
RATIONALE:
Prompt engineering focuses on designing inputs that guide a generative AI model to produce
accurate, relevant, and useful outputs without modifying the model's weights. The goal is to elicit
the best possible response through careful input design, not to alter the underlying model
architecture or training .
QUESTION 2:
Which of the following is an example of a zero-shot prompt?
A. "Here is an example: 'Cat → Gato'. Now translate 'Dog'."
B. "Translate 'Hello' to Spanish." (without examples)
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."
ANSWER:
B. "Translate 'Hello' to Spanish." (without examples)
RATIONALE:
Zero-shot prompting means the model receives no examples and must rely solely on its pre-trained
knowledge. Option A is an example of one-shot prompting (one example provided), Option C is few-
shot prompting (5 examples), and Option D is few-shot prompting (3 examples) .
QUESTION 3:
What does the "temperature" parameter control in LLM generation?
A. Length of output
B. Grammar correctness
C. Randomness or creativity of outputs
D. Training data size
ANSWER:
C. Randomness or creativity of outputs
pg. 3
, WGU D685 EXAM
RATIONALE:
Temperature is a sampling parameter that controls the probability distribution of token selection.
Lower temperature (e.g., 0.2) makes outputs more deterministic and predictable; higher
temperature (e.g., 0.9) increases randomness, diversity, and creativity .
QUESTION 4:
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
ANSWER:
B. The most deterministic, greedy decoding
RATIONALE:
At temperature 0, the model always selects the token with the highest probability at each step,
producing deterministic outputs. The same prompt will generate the same (or very similar) response
each time, making this setting ideal for tasks requiring consistency and factual accuracy .
QUESTION 5:
What is the purpose of the "top_p" (nucleus sampling) parameter?
A. Limit the number of tokens generated
B. Choose from the smallest set of tokens whose cumulative probability exceeds p
C. Adjust grammar style
D. Increase prompt length
ANSWER:
B. Choose from the smallest set of tokens whose cumulative probability exceeds p
RATIONALE:
Top-p (nucleus sampling) dynamically selects the smallest set of words whose cumulative probability
exceeds a threshold (p). For example, top-p=0.9 selects the set of words that cumulatively represent
90% of the probability mass, creating more diverse and coherent outputs than top-k sampling in
many cases .
QUESTION 6:
A user writes, "You are a high school math teacher. Explain the Pythagorean theorem." Which
prompt component is "You are a high school math teacher"?
A. Constraint
B. Format specification
C. Persona assignment
D. Output length specification
pg. 4
