HOTSPOT
-
You need to recommend an AI solution for each task. The solutions must use prebuilt AI capabilities to reduce development time.
What should you recommend for each task? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Extract information from invoices and credit notes: Azure Document Intelligence in Foundry Tools
Identify discussion topics in customer service call recordings: Azure Speech in Foundry Tools
Detect customer sentiment and opinions: Azure Language in Foundry Tools
Explanation: Use prebuilt document extraction for invoices, speech services for call recordings, and language services for sentiment analysis.
Question 30
Your company has an AI solution that uses a prebuilt Azure OpenAI model to generate content.
You need to reduce the cost of solution while minimizing the impact on the quality of the generated output.
Which two actions should you perform? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
A. Switch to an alternate model.
B. Apply content moderation.
C. Optimize the prompts.
D. Decrease the number of hosting hours for the model.
E. Fine-tune the existing model.
Show Answer
Correct Answer: A, C
Explanation: Switching to a smaller or more cost-efficient Azure OpenAI model can significantly reduce per-token costs while maintaining acceptable quality for many workloads. Optimizing prompts reduces token usage and unnecessary calls, lowering costs with minimal impact on output quality. Content moderation adds processing rather than reducing generation cost, hosting hours are not how prebuilt Azure OpenAI models are billed, and fine-tuning typically adds cost rather than reducing it.
Question 31
Your company sells hiking and camping gear online.
You need a generative AI solution that can interact with customers, ask questions about their needs, and escalate to a human agent if necessary.
What solution should you use?
A. a chatbot
B. predictive AI
C. a recommendation engine
D. computer vision
Show Answer
Correct Answer: A
Explanation: A chatbot is the appropriate generative AI solution for interacting with customers in natural language, asking follow-up questions to understand their needs, recommending products, and escalating conversations to a human agent when required. Predictive AI forecasts outcomes, recommendation engines suggest products but do not manage conversational interactions, and computer vision analyzes images.
Question 32
HOTSPOT
-
Select the answer that correctly completes the sentence.
Show Answer
Correct Answer: can produce new and original content.
Explanation: Generative AI creates new content, while predictive AI focuses on forecasting or classifying outcomes from existing data. Dataset size and accuracy are not the defining distinction.
Question 33
Your company plans to use generative AI to help build a website that will showcase various existing products.
Which capability best describes a benefit of using generative AI for this project? More than one answer choice may achieve the goal. Select the BEST answer.
A. creating product descriptions based on product specifications
B. designing a new product based on customer requirements
C. translating product descriptions into a different language
D. analyzing product sales to identify patterns and trends
Show Answer
Correct Answer: A
Explanation: Creating product descriptions from product specifications is a core generative AI capability that directly supports building a website showcasing existing products. Translating text is an AI capability but is not the best fit for the stated goal, designing a new product changes the project scope, and analyzing sales patterns is predictive/analytical rather than generative.
Question 34
HOTSPOT
-
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Yes
No
Yes
Explanation: Prompt engineering guides model behavior. Instructions specify the task, while examples are a separate prompt component. Context provides relevant background and information for generating the response.
Question 35
HOTSPOT
-
Select the answer that correctly completes the sentence.
Show Answer
Correct Answer: accuracy and relevance of AI-generated responses.
Explanation: Prompt engineering improves how the model is guided at inference time, leading to more accurate and relevant outputs. It does not increase storage capacity or model training time.
Question 36
HOTSPOT
-
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: No
No
Yes
Explanation: Text-to-image models generate images, not translations. Predictive analytics forecasts or classifies rather than creating new content. Generative AI chatbots can provide personalized conversations and product recommendations.
Question 37
HOTSPOT
-
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: No
Yes
No
Explanation: Prompt engineering does not change a model's training; it improves how inputs are written. Good prompt engineering emphasizes clear, concise, context-rich instructions rather than maximizing token count.
Question 38
You have a large language model (LLM) that was pretrained by using public data.
You want the LLM to generate responses that incorporate frequently updated proprietary content, such as internal documents and knowledge bases.
You need to recommend a solution to ensure that the LLM uses the most current information without retraining the model.
What should you include in the recommendation?
A. Retrieval Augmented Generation (RAG)
B. prompt engineering
C. content filtering
D. model fine-tuning
Show Answer
Correct Answer: A
Explanation: Retrieval Augmented Generation (RAG) retrieves relevant, up-to-date information from external proprietary sources at inference time and provides it as context to the LLM. This allows the model to use frequently changing internal documents and knowledge bases without retraining or fine-tuning. Prompt engineering cannot inject current proprietary knowledge by itself, content filtering is for safety/moderation, and fine-tuning requires retraining and does not keep pace with frequently updated content.
$19
Get all 99 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
