AIF-C01 practice questions 381–390

1. Question 381 · 417 in bank

   A company wants to use a large language model (LLM) to generate responses based on company data. Which strategy will meet this requirement?

   • AUse first-party pre-trained models from Amazon Bedrock.
   • BUse pre-trained open source models.
   • CFine-tune a custom model on company data.
   • DUse pre-trained third-party models from Amazon Bedrock.

   Show answer

   Answer: C

   Next question

2. Question 382 · 417 in bank

   What is an example of structured data?

   • AA file of text comments from an online forum
   • BA compilation of video files that contains news broadcasts
   • CA CSV file that consists of measurement data
   • DTranscribed conversations between call center agents and customers

   Show answer

   Answer: C

   Next question

3. Question 383 · 417 in bank

   A company uses foundation models (FMs) to automate daily tasks. An AI practitioner at the company is creating system instructions that include context that is relevant to the tasks. The AI practitioner wants to save and reuse the instructions in daily interactions with FMs in Amazon Bedrock. Which Amazon Bedrock solution will meet these requirements?

   • AKnowledge Bases
   • BGuardrails
   • CPlaygrounds
   • DPrompt management

   Show answer

   Answer: D

   Next question

4. Question 384 · 417 in bank

   A company maintains a large product catalog with detailed descriptions. The company wants to build an AI assistant to answer customer questions about the products. However, the company’s labeled training data is limited. Which solution will meet these requirements with the LEAST implementation effort?

   • AUse a Retrieval Augmented Generation (RAG) architecture to query the product database at runtime. Provide relevant, unmodified product descriptions as context for the foundation model (FM).
   • BFine-tune a foundation model (FM) on the restricted labeled data. Automatically refresh the model with novel product details weekly for accuracy.
   • CDeploy a foundation model (FM) for each product category. Implement a routing layer to direct customer queries to the appropriate specialized model.
   • DCreate a new custom foundation model (FM) that is trained on the product database. Optimize the FM for minimal token usage during inference.

   Show answer

   Answer: A

   Next question

5. Question 385 · 417 in bank

   A company is deploying a new AI application to generate content for internal users. Which strategy will make the application output more deterministic?

   • ADecreasing the temperature
   • BIncreasing the learning rate
   • CSetting stop sequences
   • DSetting the token count

   Show answer

   Answer: A

   Next question

6. Question 386 · 417 in bank

   A company runs an application on servers in an Amazon VPC. The company’s application uses Amazon Bedrock APIs for AI features. The company does not want API calls to travel across the public internet. Which solution will meet this requirement?

   • AUse AWS PrivateLink to establish a private connection between the Amazon VPC and Amazon Bedrock.
   • BSign API requests by using an access key ID and a secret access key that is associated with an IAM principal.
   • CMove the application to an on-premises server. Make API calls to the public endpoint of Amazon Bedrock.
   • DEncrypt the data in transit from clients to the APIs that have been implemented in the Amazon VPC. Encrypt the data in transit for API calls from the Amazon VPC to Amazon Bedrock.

   Show answer

   Answer: A

   Next question

7. Question 387 · 417 in bank

   A financial company uses an ML model to detect potentially fraudulent transactions. The company needs to ensure that some types of predictions receive review by human analysts before the company acts upon the predictions. Which AWS solution will meet this requirement?

   • AAmazon SageMaker Clarify
   • BAmazon SageMaker Ground Truth
   • CAmazon Augmented AI (Amazon A2I)
   • DAmazon SageMaker Model Monitor

   Show answer

   Answer: C

   Next question

8. Question 388 · 417 in bank

   Which strategy will evaluate the performance of a foundation model (FM) in real-world applications?

   • AConducting A/B testing with users in a controlled environment
   • BHuman evaluation by subject matter experts
   • CMeasuring the model’s accuracy on a training dataset
   • DAnalysis of the model’s internal representations and attention patterns

   Show answer

   Answer: A

   Next question

9. Question 389 · 417 in bank

   A company is building a chatbot. The chatbot uses a large language model (LLM) and answers customer questions about products. The company wants the chatbot to answer only product questions. The company does not want the chatbot to answer questions about other topics. Which solution will meet these requirements with the LEAST operational overhead?

   • ASet guardrails on the LLM prompt template.
   • BWrite custom application logic to identify questions about other topics.
   • CReduce the information the LLM can access.
   • DSet the temperature parameter value to a lower number.

   Show answer

   Answer: A

   Next question

10. Question 390 · 417 in bank

    A company is building a large language model (LLM)-based AI assistant to support service agents by automatically managing customer inquiries. The company wants to reduce the effort that customer service agents require during support calls. The company needs to select a metric to evaluate the AI assistant against one of the company’s business objectives. Which metric will meet these requirements?

    • AWebsite engagement rate
    • BAverage call duration
    • CAgent attrition rate
    • DFirst contact resolution rate

    Show answer

    Answer: B

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AIF-C01 practice, question 381. 417 questions available.