Practical-Applications-of-Prompt無料試験問題と解答PDF最新問題2026年06月
最新Practical-Applications-of-Prompt試験問題集で最近更新された52問題
質問 # 18
A person wants to use AI to make a technical document easier to comprehend. Which prompt engineering solution is most effective to achieve this goal?
- A. Include reading-level limitations with "at a tenth-grade reading level"
- B. Correctly instruct the model with the keywords "translating" and "document"
- C. Give a list of appropriate words with the phrase "using these words"
- D. Ask the model to create another version with "read and summarize"
正解：A
解説：
The most effective way to optimize AI for clarity and comprehension is toinclude reading-level limitations.
While "summarizing" (Option B) shortens the text, it doesn't necessarily make the remaining language simpler. However, specifying a "tenth-grade reading level" (or "Explain it like I'm five") provides the AI with a very specific linguistic constraint. It forces the model to swap complex jargon for common synonyms, use shorter sentence structures, and avoid passive voice.
This technique is a form ofOutput Constraint. Reading levels are well-defined metrics that AI models can emulate because they have been trained on vast amounts of graded educational material. By setting this boundary, the user ensures the output is accessible to a broader audience without losing the core technical meaning. In practical professional settings-such as translating a medical white paper for a patient or a legal contract for a small business owner-this type of prompting is essential. It transforms dense, "impenetrable" text into actionable information, demonstrating how specific constraints can be used to reformat and simplify complex data sets effectively.
質問 # 19
What is the principle of ethics that is ensured by creating mechanisms to assign responsibility for AI actions and decisions?
- A. Accountability
- B. Fairness
- C. Societal impact
- D. Transparency
正解：A
解説：
The principle ofAccountabilityis centered on the requirement that there must be an identifiable person or entity responsible for the outcomes of an AI system's actions. As AI systems become more autonomous, the
"responsibility gap" becomes a significant ethical risk. Establishing accountability means creating clear frameworks-legal, organizational, and technical-to ensure that when an AI makes a mistake (such as an incorrect medical diagnosis or a biased financial decision), there is a mechanism for recourse, explanation, and correction.
In the context of prompt engineering, accountability is often managed through "human-in-the-loop" systems.
This ensures that while the AI may generate the initial draft or decision-making logic, a human remains the ultimate authority who "signs off" on the result. Accountability also involves "Auditability"-the ability for third parties to review the AI's logs and decision-making history. Without accountability, AI deployment can lead to "organized irresponsibility," where no one takes ownership of systemic failures. By embedding accountability into the lifecycle of an AI project, organizations protect themselves and their users, ensuring that the technology serves as a tool for human progress rather than an unchecked black box.
質問 # 20
Which content creation tool specializes in versatile image creation through detailed text prompts?
- A. Invideo
- B. Midjourney
- C. DALL-E
- D. ChatGPT
正解：B
解説：
Midjourneyis a generative AI tool that specifically specializes in high-quality, versatile image creation through sophisticated text prompts. While other tools like DALL-E are integrated into larger ecosystems (like OpenAI's ChatGPT), Midjourney has gained a reputation for its distinct artistic style, high resolution, and deep "parameter" controls that allow prompt engineers to fine-tune lighting, camera angles, and textures.
Midjourney operates primarily through a Discord interface, where users utilize "slash commands" (like
/imagine) to initiate generations. It is favored by designers and concept artists because of its ability to interpret complex, evocative language into visually stunning outputs. Unlike ChatGPT, which is primarily a text-based LLM, Midjourney is a "Diffusion Model" specifically trained on image-caption pairs. Evaluating Midjourney as a medium requires understanding that the "syntax" of the prompt differs from text models; it relies heavily on artistic descriptors, style references (e.g., "unreal engine," "octane render"), and aspect ratio constraints to achieve the desired outcome.
質問 # 21
Which major challenge has been an issue for AI systems?
- A. Generating video content
- B. Analyzing vast amounts of data
- C. Processing unstructured data
- D. Lacking ethical reasoning
正解：D
解説：
One of the most significant and persistent challenges in the field of Artificial Intelligence is the lack of inherent ethical reasoning. AI models operate based on mathematical probabilities and patterns found within their training data; they do not possess a moral compass, a sense of justice, or an understanding of social nuances unless specifically programmed or constrained by human-defined rules. This often leads to issues where an AI might generate biased, harmful, or socially insensitive outputs because it is simply reflecting the biases present in its training set without any ethical filter.
While AI is actually quite proficient at analyzing vast amounts of data and is increasingly capable of processing unstructured data and generating video, the "black box" nature of its decision-making makes ethical alignment difficult. Ensuring that an AI respects privacy, avoids discrimination, and adheres to human values requires significant external intervention, such as Reinforcement Learning from Human Feedback (RLHF). The challenge lies in the fact that ethics are often subjective and context-dependent, making it nearly impossible to encode a universal moral code into a machine. This lack of ethical reasoning is why human oversight remains a critical component of AI deployment, especially in high-stakes fields like law, healthcare, and autonomous systems.
質問 # 22
A person wants to use AI to digitize receipts for expense tracking. Which advanced AI tool should be used?
- A. Voice recognition
- B. Speech synthesis
- C. Optical character recognition
- D. Virtual personal assistant
正解：C
解説：
To digitize physical documents like receipts, the necessary technology isOptical Character Recognition (OCR). OCR is a specialized AI field that involves the conversion of images of typed, handwritten, or printed text into machine-encoded text. When you take a photo of a receipt, the AI analyzes the pixels to identify the shapes of letters and numbers, then translates those shapes into digital characters that can be stored in a database or an Excel spreadsheet.
In the context of expense tracking, advanced OCR does more than just "read" the text; it uses "intelligent character recognition" to understand the layout. It can identify which number is the "Total," which is the
"Tax," and which is the "Date" by looking at their positions on the page and the keywords nearby. This makes OCR an essential bridge between the physical and digital worlds. While a "Virtual personal assistant" (Option B) mightusean OCR tool to help you, the specific technology doing the work of digitization is OCR. It saves hours of manual data entry and reduces the human error associated with typing in long strings of financial data, making it a powerful "practical application" of AI in business and personal finance.
質問 # 23
A member of a middle pre-algebra class is having a difficult time graphing a line for a homework assignment.
In order to get help, the student enters the prompt "help with math" into an AI system. Which change should the student make to the prompt to generate a better outcome?
- A. Make the prompt a full sentence for correctness
- B. Include scores from the most recent assignments
- C. Give context on why the help is needed
- D. Include personal details, such as their first and last name
正解：C
解説：
The student's initial prompt, "help with math," is a classic example of an underspecified prompt. To optimize the outcome, the student mustgive context on why the help is needed. In prompt engineering, context is the information that surrounds the core request to give it meaning. By explaining that they are in a "middle pre- algebra class" and are specifically struggling with "graphing a line," the student provides the AI with the necessary boundaries to provide an age-appropriate and topic-specific explanation.
Without this context, the AI might provide a high-level calculus proof or a simple elementary addition example, neither of which solves the student's problem. Providing context allows the AI to "zoom in" on the specific pain point. Effective optimization often involves adding the "what" (graphing a line), the "who" (a pre-algebra student), and the "why" (trouble with a homework assignment). This ensures the AI adopts the correct educational level and provides a step-by-step breakdown suitable for a middle schooler, rather than a generic or overly complex mathematical response.
質問 # 24
What is an advantage of using Personas in prompt engineering?
- A. Efficient use of system memory
- B. Highly relevant responses
- C. Better memory of past conversations
- D. Greater response speed
正解：B
解説：
The primary advantage of using a persona (e.g., "Act as a senior data scientist" or "You are a friendly high school tutor") is the generation ofhighly relevant responses. A persona acts as a sophisticated filter for the AI's vast training data. When a persona is assigned, the model narrows its focus to the tone, vocabulary, and problem-solving frameworks that are most characteristic of that specific role. This ensures that the output is stylistically and substantively aligned with the user's expectations.
For instance, if you ask for financial advice without a persona, you may get a generic list of tips. If you use the persona of a "conservative financial planner for retirees," the response will prioritize low-risk investments and capital preservation. This relevance is key to professional applications where the "voice" of the output is just as important as the information itself. Personas essentially prime the model's "associative memory" to pull from the most appropriate clusters of data, making the interaction feel more like a consultation with an expert rather than a search query.
質問 # 25
What is one example of a task in which natural language processing (NLP) algorithms are employed?
- A. Textual data cleaning
- B. Interpreting raw values
- C. Numerical data cleaning
- D. Increasing raw data precision
正解：A
解説：
Natural Language Processing (NLP) is a branch of AI that focuses on the interaction between computers and human language. One of its most practical and widespread applications isTextual data cleaning. When dealing with large datasets of unstructured text-such as customer reviews, social media posts, or support tickets-the data is often "noisy," containing typos, slang, irrelevant HTML tags, or inconsistent formatting.
NLP algorithms are used to standardize this data through techniques like tokenization (breaking text into words), stemming or lemmatization (reducing words to their root form), and "stop word" removal (filtering out common words like "the" or "is" that don't add semantic value). This cleaning process is essential before any higher-level analysis, such as sentiment analysis or topic modeling, can take place. If the data isn't cleaned, the resulting AI model will be less accurate. Unlike "Numerical data cleaning" (Option D), which deals with outliers or missing values in numbers, textual data cleaning requires an understanding of linguistic rules and context, which is the core strength of NLP. Effective prompt engineering often involves asking an AI to perform these cleaning tasks to prepare a dataset for more complex reasoning or summarization.
質問 # 26
A user uses an AI model to predict weather patterns. However, the model consistently predicts temperatures that are off by about five degrees. Which form of bias is associated with this phenomenon?
- A. Measurement bias
- B. Selection bias
- C. Confirmation bias
- D. Sampling bias
正解：A
解説：
The phenomenon where an AI consistently produces results that deviate from the truth by a specific margin (in this case, five degrees) is known asMeasurement bias. This typically occurs when the data used to train the model was collected using faulty, poorly calibrated, or inconsistent tools. If the thermometers used to gather the historical weather data were all consistently off by five degrees, the AI will learn and replicate that systemic error as if it were a factual pattern.
Unlike "Sampling bias" (which involves who or what is included in the data) or "Confirmation bias" (which involves the user seeking data that fits their beliefs), Measurement bias is a technical flaw in the data collection phase. It is particularly dangerous because the model may appear to be "consistent" and "reliable," but it is actually consistently wrong. In the field of AI ethics and data integrity, identifying measurement bias is crucial because it requires the user to go back to the source sensors or the data entry process to find the
"skew." Correcting this bias isn't a matter of changing the prompt, but rather of re-calibrating the training data to ensure it accurately reflects the real-world environment it is meant to predict.
質問 # 27
Which factor should be considered when writing generative AI prompts?
- A. Time of day
- B. Location
- C. Uniqueness
- D. Scope
正解：D
解説：
When engineering a prompt, determining the "Scope" is vital for achieving a high-quality response. Scope refers to the boundaries and breadth of the request. A prompt with a scope that is too broad (e.g., "Tell me everything about history") will result in a superficial, overly generalized, and likely unhelpful response.
Conversely, a prompt with a scope that is too narrow might exclude necessary context.
Effective prompt engineering involves "right-sizing" the scope to match the user's specific needs. This includes defining the timeframe, the specific sub-topics to be covered, and the level of detail required. By managing the scope, the user prevents the AI from "hallucinating" or filling in gaps with irrelevant information. It also helps manage the model's token limit and ensures that the most important information is prioritized in the output. While factors like uniqueness or location might be relevant in very specific niche cases, "Scope" is a universal pillar of prompt construction. It ensures that the AI stays focused on the task at hand, delivering a concentrated and accurate response that fits within the user's practical requirements.
質問 # 28
A team of historians wants to use AI-based tools to aid in the research of the history of Europe's agricultural equipment. What is the importance of writing effective prompts in the research?
- A. It ensures that researchers remain focused.
- B. It ensures that interpretations are innovative.
- C. It determines the level of importance of the research.
- D. It reduces the need for reliance on multiple sources.
正解：A
解説：
In academic and historical research, the sheer volume of available data can easily lead to "scope creep" or tangential exploration. Writing effective prompts is crucial because it ensures that researchers remain focused on their specific inquiry. When dealing with a broad subject like "Europe's agricultural equipment," an unstructured prompt might return a generalized history of farming. However, an effective prompt-specifying the region (e.g., Western Europe), the era (e.g., the Industrial Revolution), and the specific type of equipment (e.g., steam-powered threshing machines)-acts as a navigational guide for the AI.
This focus is essential for maintaining the integrity of the research process. It prevents the AI from generating irrelevant "filler" content and forces the output to adhere to the specific historical parameters defined by the team. While AI can assist in synthesizing information, it cannot determine the "importance" of research (which is a human value judgment) nor should it replace the need for multiple sources (as verification is still required). By refining the prompt to include specific constraints and objectives, historians can use AI as a precision tool to uncover specific data points and trends, ensuring that the resulting analysis stays aligned with the original research goals.
質問 # 29
A lawyer needs to interact with a database to search for cases relating to college admissions. What is a benefit of writing effective prompts when interacting with the database?
- A. Greater capacity for unstructured data storage
- B. Data modification for improved applicability
- C. Prevention of sifting through irrelevant results
- D. Automatic expansion to include more data
正解：C
解説：
For professionals dealing with vast amounts of specialized information, such as lawyers, the primary benefit of effective prompt engineering is the prevention of sifting through irrelevant results. Legal databases are massive, containing millions of precedents, statutes, and opinions. A vague prompt like "Find cases about schools" would return thousands of results, most of which would be useless to a specific case regarding college admissions.
By using specific keywords, Boolean logic, and contextual constraints within the prompt (e.g., "Search for U.
S. Supreme Court cases from 2000-2023 specifically addressing affirmative action in private university undergraduate admissions"), the lawyer drastically narrows the search field. This precision is the essence of effective prompting in a professional environment. It saves significant time and cognitive energy by ensuring that the AI or search algorithm acts as a high-resolution filter. This "signal-to-noise" optimization allows the professional to focus on the high-value task of legal analysis rather than the low-value task of manual data sorting. Effective prompts turn a mountain of data into a curated list of relevant evidence.
質問 # 30
What is an example of a prompt that has an appropriate level of specificity?
- A. "Provide an overview of state representative election laws in Iowa."
- B. "Explain how guidelines and regulations are established for businesses."
- C. "Tell me about physics, chemistry, biology, and astronomy."
- D. "Tell me the best classes to take when attending a university."
正解：A
解説：
Specificity is the cornerstone of effective prompt engineering. A specific prompt provides clear boundaries and a narrow focus, which prevents the AI from generating generic or overwhelming amounts of irrelevant information. Option C, "Provide an overview of state representative election laws in Iowa," is the best example because it defines three critical parameters: theSubject(election laws), theScope(state representative level), and theLocation/Jurisdiction(Iowa).
In contrast, options A and D are far too broad; asking for an overview of four major sciences or all business regulations would result in a superficial summary that lacks depth. Option B is subjective and lacks context, as "best classes" depends entirely on the student's major and career goals. By specifying the state and the specific legislative body, the user in Option C allows the AI to access a targeted subset of its training data. In practical applications, this level of specificity significantly reduces the risk of "hallucinations" or factual errors, as the model is guided to a precise factual domain. This is essential in professional research where accuracy and relevance are prioritized over general knowledge.
質問 # 31
An AI model was trained on historical loan data. A loan officer has noticed that the model disproportionately suggests to refuse loans to people who live in a particular area. What is the type of bias described in the scenario?
- A. Algorithmic bias
- B. Measurement bias
- C. Selection bias
- D. Sampling bias
正解：A
解説：
The scenario describesAlgorithmic bias, which occurs when an AI system reflects and potentially amplifies the prejudices or inequalities present in the historical data it was trained on. In this case, if historical lending practices were discriminatory toward specific neighborhoods (a practice known as "redlining"), the AI model treats the resulting "denial" patterns as a mathematical rule. It learns that living in a certain zip code is a predictor of loan failure, even if the individual applicants are creditworthy.
This is a major ethical concern in prompt engineering and AI deployment because the "bias" is not a glitch in the code, but a reflection of systemic human bias encoded into the model's logic. It differs from "Sampling bias" (which would occur if the model only looked at one city) or "Measurement bias" (which involves faulty sensors). Algorithmic bias is particularly insidious because it can give discriminatory decisions a "veneer of objectivity," making it harder for human operators to spot the unfairness. Addressing this requires rigorous data auditing and the use of "fairness constraints" to ensure that the AI does not penalize individuals based on protected characteristics or proxy variables like geography.
質問 # 32
A lawyer needs to interact with a database to search for cases relating to college admissions. What is a benefit of writing effective prompts when interacting with the database?
- A. Greater capacity for unstructured data storage
- B. Data modification for improved applicability
- C. Prevention of sifting through irrelevant results
- D. Automatic expansion to include more data
正解：C
解説：
For professionals dealing with vast amounts of specialized information, such as lawyers, the primary benefit of effective prompt engineering is the prevention of sifting through irrelevant results. Legal databases are massive, containing millions of precedents, statutes, and opinions. A vague prompt like "Find cases about schools" would return thousands of results, most of which would be useless to a specific case regarding college admissions.
By using specific keywords, Boolean logic, and contextual constraints within the prompt (e.g., "Search for U.
S. Supreme Court cases from 2000-2023 specifically addressing affirmative action in private university undergraduate admissions"), the lawyer drastically narrows the search field. This precision is the essence of effective prompting in a professional environment. It saves significant time and cognitive energy by ensuring that the AI or search algorithm acts as a high-resolution filter. This "signal-to-noise" optimization allows the professional to focus on the high-value task of legal analysis rather than the low-value task of manual data sorting. Effective prompts turn a mountain of data into a curated list of relevant evidence.
質問 # 33
Which strategy is effective for a company to promote the ethical use of AI?
- A. Foster collaboration among diverse stakeholders to address ethical challenges
- B. Encourage users to ethically evaluate AI responses using their personal data
- C. Require employees to use an AI model to make a decision for any ethical dilemma
- D. Use an AI system to evaluate job applicants based on fair and ethical criteria
正解：A
解説：
The most effective strategy for promoting ethical AI is tofoster collaboration among diverse stakeholders.
Ethics in AI is not a purely technical problem that can be "solved" with code; it is a socio-technical challenge that requires input from various perspectives, including ethicists, legal experts, social scientists, engineers, and, most importantly, the communities affected by the AI.
Diverse collaboration helps identify "blind spots" that a homogenous technical team might miss. For example, a developer might not realize that a specific data feature is a proxy for race or gender, but a sociologist or a community advocate might recognize it immediately. By bringing these voices together, a company can develop "Ethics by Design" frameworks that proactively address bias, transparency, and safety issues before the AI is deployed. This approach aligns with the principle of "Multidisciplinary Oversight," ensuring that the AI's goals are aligned with human values. Relying purely on the AI to solve its own ethical dilemmas (Option A) is dangerous, as the AI lacks a true moral compass. Instead, human-led collaboration ensures that technology remains a servant to societal well-being.
質問 # 34
A person is preparing for an upcoming speech and wants to use generative AI to help prepare for the speech.
What should the person do before writing a prompt?
- A. Upload a personal audio sample
- B. Identify the goal of the speech
- C. Choose a scripting language
- D. Write a rough draft of the speech
正解：B
解説：
The most critical step in the "pre-prompting" phase is the clear identification of the objective. Before interacting with a generative AI, the user must identify the goal of the speech. This foundational step dictates every other element of the prompt, including the persona, tone, and specific constraints. For example, a speech intended to persuade a group of investors requires a radically different linguistic approach than a speech intended to toast a friend at a wedding.
By identifying the goal first, the user can construct a prompt that provides the AI with a clear "definition of success." In practical applications, this is often referred to as the "Intent" phase. If a user skips this and goes straight to writing a draft or providing samples, the AI may generate content that is stylistically correct but fundamentally misses the mark regarding the intended outcome. Clear goals allow the user to evaluate the AI's output critically-checking if the generated text actually serves the purpose of informing, persuading, entertaining, or inspiring. Without a defined goal, prompt engineering becomes a trial-and-error process rather than a strategic exercise.
質問 # 35
A user is crafting a prompt and includes both the goal and the context within the text of the prompt. What is a benefit of crafting the prompt in this way?
- A. Faster rate of response
- B. Improved interface appeal
- C. Greater interaction effectiveness
- D. Reduced computational load
正解：C
解説：
Combining a cleargoalwith richcontextis the gold standard for achievinggreater interaction effectiveness.
The goal tells the AIwhatto achieve (the destination), while the context explains thecircumstancessurrounding the task (the map). When these two elements are present, the AI can generate a response that is not only factually correct but also relevant to the user's specific situation. Effectiveness in AI interactions is measured by how closely the output meets the user's needs on the first try.
When a prompt lacks a goal, the AI might provide a great summary of a topic but fail to perform the required action. When it lacks context, it might perform the action in a way that is inappropriate for the audience. By merging them, the user minimizes "drift"-the tendency for AI to wander into irrelevant topics. This leads to a more professional, tailored, and high-quality interaction. In practical scenarios, such as drafting a corporate policy or creating a marketing strategy, the synergy between goal and context ensures that the AI understands the "big picture," resulting in a much more effective and usable first draft.
質問 # 36
What is an advantage that comes from generative AI interfaces that are designed well?
- A. They allow users to specify the context for generating outputs.
- B. They filter output that contains errors and bias.
- C. They give each user an experience with unique generated outputs.
- D. They allow users to avoid exposure to misinformation.
正解：A
解説：
A well-designed generative AI interface prioritizes user control and clarity. One of the most significant advantages of a high-quality interface is that it provides the necessary fields or conversational flow to allow users to specify the context for generating outputs. In the realm of prompt engineering, context is the
"background information" that helps the model understand the specific environment, audience, or constraints of the task. Without a well-designed interface, users might provide vague prompts, leading to generic or irrelevant results.
Effective interfaces often guide the user through "prompt priming"-allowing them to set the scene (e.g., "I am writing a report for a CEO" vs. "I am writing a blog post for teenagers"). By enabling the user to easily input parameters such as tone, format, and specific background data, the interface ensures the AI has a narrow enough focus to be useful. While AI models still struggle with inherent bias or misinformation (options A and D), a good interface mitigates these risks by encouraging specific, context-rich inputs that ground the AI's logic in the user's actual needs. This results in outputs that are significantly more relevant and actionable compared to unguided interactions.
質問 # 37
A person provides the content of an email to an AI model and asks it to identify whether the email is a promotion. The person prompts the model repeatedly and takes the response most often provided. Which prompting technique is described?
- A. Chain of thought (COT)
- B. Self-consistency
- C. Least to most
- D. Generated knowledge
正解：B
解説：
The technique described isSelf-consistency. This is an advanced optimization strategy used to improve the reliability of AI outputs, particularly in classification or reasoning tasks. Because generative AI is probabilistic, it might provide different answers to the same prompt across different sessions. To mitigate the risk of a "one-off" error, the user prompts the model multiple times for the same task and applies a "majority vote" system to select the final answer.
This approach is based on the principle that if multiple different reasoning paths lead to the same conclusion, that conclusion is significantly more likely to be correct. In the case of identifying a promotional email, the model might occasionally misinterpret a professional newsletter as a personal message. However, if it classifies it as a "promotion" in four out of five attempts, the user can be much more confident in that result.
Self-consistency is a critical tool for "de-risking" AI applications in data labeling and sentiment analysis, where high precision is required and the cost of a false positive is high. It leverages the model's internal variance to find the most stable and logically sound output.
質問 # 38
Which activity is facilitated by natural language processing?
- A. Verifying experiment measurements
- B. Checking for grammar errors
- C. Calculating numerical data statistics
- D. Managing parallel computing
正解：B
解説：
Checking for grammar errorsis a quintessential NLP task. Modern grammar checkers (like Grammarly or the built-in tools in Word and ChatGPT) do not just look for misspelled words; they utilize NLP to understand the syntactic structure of a sentence. This allows the AI to identify complex issues such as subject-verb disagreement, dangling modifiers, and improper tense usage.
NLP models are trained on the rules of linguistics and large corpora of well-written text, allowing them to predict what a "correct" sentence should look like. This facilitates more than just mechanical correction; it allows the AI to suggest improvements in tone, clarity, and conciseness. Because the AI "understands" the relationship between different parts of speech, it can offer context-aware suggestions. For example, it can distinguish between "there," "their," and "they're" based on the surrounding words-a task that a simple spell- checker cannot do. This application is foundational to prompt engineering because users often use AI as an editor. By facilitating high-quality grammar and style checking, NLP allows for more professional communication and ensures that the final output of any prompt is polished and ready for a human audience.
質問 # 39
......
WGU Practical-Applications-of-Promptリアル2026年最新のブレーン問題集で模擬試験問題集：https://jp.fast2test.com/Practical-Applications-of-Prompt-premium-file.html
Practical-Applications-of-Prompt試験問題リアルPractical-Applications-of-Prompt練習問題集：https://drive.google.com/open?id=1YoZJEWBm0PVCA3wRZbOOkkvJ9v1afjLY