WGU D685 OBJECTIVE ASSESSMENT 2
NEWEST 2025/2026 ACTUAL EXAM D685
PRACTICAL APPLICATIONS OF PROMPT
OA EXAM
COMPLETE 100 REAL EXAM QUESTIONS AND CORRECT
VERIFIED ANSWERS WITH RATIONALES
EXAM OVERVIEW
The WGU D685 Objective Assessment 2 evaluates mastery of the practical
applications of prompt engineering. The exam assesses ability to apply
best practices, navigate ethical dilemmas, ensure regulatory compliance,
and optimize interactions with AI models in professional settings.
Core Domains Covered:
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, 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
,SECTION 1: PROMPT ENGINEERING FUNDAMENTALS
(Questions 1-20)
Q1. What is prompt engineering?
A) A software development methodology for building AI systems from
scratch
B) The practice of designing and refining inputs to AI language models to
produce desired outputs
C) A hardware optimization technique for running large language models
faster
D) A method of training neural networks using reinforcement learning
Answer: B
Rationale: Prompt engineering is the disciplined practice of crafting, refining,
and optimizing input prompts to guide AI language models toward generating
specific, accurate, and useful outputs. It involves understanding how models
interpret language and strategically structuring instructions to achieve
desired results.
Q2. What is the primary goal of prompt engineering in generative AI?
A) To write longer prompts with more details
B) To maximize the likelihood of a desired model output
C) To reduce the number of model parameters
D) To train the model from scratch using custom datasets
Answer: B
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 or architecture.
,Q3. Which of the following best describes a 'prompt' in the context of large
language models (LLMs)?
A) The GPU memory allocated to a model during inference
B) A hyperparameter used during model training
C) The input text or instruction provided to a language model to guide its
response
D) The tokenization scheme used to encode model outputs
Answer: C
Rationale: A prompt is the user-provided input—whether a question,
instruction, or statement—that serves as the starting point for an LLM's
response generation. The quality and structure of the prompt directly
influence the relevance and accuracy of the model's output.
Q4. What is "zero-shot" prompting?
A) Providing the model with many examples before asking a question
B) Asking the model to perform a task without providing any examples
C) Using a model that has not been fine-tuned on any data
D) Querying the model with an empty prompt
Answer: B
Rationale: Zero-shot prompting relies entirely on the model's pretrained
knowledge. The user provides instructions without any example inputs or
outputs. This technique works well for common, well-understood tasks but
may struggle with niche domains or specific formatting requirements.
Q5. What is "few-shot" prompting?
, A) Providing several examples of input-output pairs in the prompt before
asking the model to complete a new task
B) Fine-tuning a model on a small dataset
C) Using a reduced model size to speed up inference
D) Limiting the model response to a few words
Answer: A
Rationale: Few-shot prompting includes 2-5 examples of the desired task
within the prompt. These examples "teach" the model the expected pattern,
format, or reasoning approach without requiring model parameter updates.
Q6. In the context of prompt engineering, what is the primary purpose of
"few-shot" prompting?
A) To provide the AI with a large dataset to train on before generating a
response
B) To instruct the AI to generate a specific number of responses for a
single prompt
C) To give the AI a few examples of the desired input-output format within
the prompt itself
D) To reduce the computational cost of generating a response by limiting
the AI's context window
Answer: C
Rationale: Few-shot prompting is a technique where the prompt includes a
small number of examples that demonstrate the task. This helps the AI
understand the pattern and format required without needing extensive
fine-tuning.
Q7. What does the "temperature" parameter control in LLM generation?
NEWEST 2025/2026 ACTUAL EXAM D685
PRACTICAL APPLICATIONS OF PROMPT
OA EXAM
COMPLETE 100 REAL EXAM QUESTIONS AND CORRECT
VERIFIED ANSWERS WITH RATIONALES
EXAM OVERVIEW
The WGU D685 Objective Assessment 2 evaluates mastery of the practical
applications of prompt engineering. The exam assesses ability to apply
best practices, navigate ethical dilemmas, ensure regulatory compliance,
and optimize interactions with AI models in professional settings.
Core Domains Covered:
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, 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
,SECTION 1: PROMPT ENGINEERING FUNDAMENTALS
(Questions 1-20)
Q1. What is prompt engineering?
A) A software development methodology for building AI systems from
scratch
B) The practice of designing and refining inputs to AI language models to
produce desired outputs
C) A hardware optimization technique for running large language models
faster
D) A method of training neural networks using reinforcement learning
Answer: B
Rationale: Prompt engineering is the disciplined practice of crafting, refining,
and optimizing input prompts to guide AI language models toward generating
specific, accurate, and useful outputs. It involves understanding how models
interpret language and strategically structuring instructions to achieve
desired results.
Q2. What is the primary goal of prompt engineering in generative AI?
A) To write longer prompts with more details
B) To maximize the likelihood of a desired model output
C) To reduce the number of model parameters
D) To train the model from scratch using custom datasets
Answer: B
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 or architecture.
,Q3. Which of the following best describes a 'prompt' in the context of large
language models (LLMs)?
A) The GPU memory allocated to a model during inference
B) A hyperparameter used during model training
C) The input text or instruction provided to a language model to guide its
response
D) The tokenization scheme used to encode model outputs
Answer: C
Rationale: A prompt is the user-provided input—whether a question,
instruction, or statement—that serves as the starting point for an LLM's
response generation. The quality and structure of the prompt directly
influence the relevance and accuracy of the model's output.
Q4. What is "zero-shot" prompting?
A) Providing the model with many examples before asking a question
B) Asking the model to perform a task without providing any examples
C) Using a model that has not been fine-tuned on any data
D) Querying the model with an empty prompt
Answer: B
Rationale: Zero-shot prompting relies entirely on the model's pretrained
knowledge. The user provides instructions without any example inputs or
outputs. This technique works well for common, well-understood tasks but
may struggle with niche domains or specific formatting requirements.
Q5. What is "few-shot" prompting?
, A) Providing several examples of input-output pairs in the prompt before
asking the model to complete a new task
B) Fine-tuning a model on a small dataset
C) Using a reduced model size to speed up inference
D) Limiting the model response to a few words
Answer: A
Rationale: Few-shot prompting includes 2-5 examples of the desired task
within the prompt. These examples "teach" the model the expected pattern,
format, or reasoning approach without requiring model parameter updates.
Q6. In the context of prompt engineering, what is the primary purpose of
"few-shot" prompting?
A) To provide the AI with a large dataset to train on before generating a
response
B) To instruct the AI to generate a specific number of responses for a
single prompt
C) To give the AI a few examples of the desired input-output format within
the prompt itself
D) To reduce the computational cost of generating a response by limiting
the AI's context window
Answer: C
Rationale: Few-shot prompting is a technique where the prompt includes a
small number of examples that demonstrate the task. This helps the AI
understand the pattern and format required without needing extensive
fine-tuning.
Q7. What does the "temperature" parameter control in LLM generation?
