AWS Certified AI Practitioner417 questions across 42 pages are complete and free, with no account or card.
417 questions in this bank
Free access · progress saved on this device
A company needs to log all requests made to its Amazon Bedrock API. The company must retain the logs securely for 5 years at the lowest possible cost. Which combination of AWS service and storage class meets these requirements? (Choose two.)
Answer: AD
An ecommerce company wants to improve search engine recommendations by customizing the results for each user of the company’s ecommerce platform. Which AWS service meets these requirements?
Answer: A
A hospital is developing an AI system to assist doctors in diagnosing diseases based on patient records and medical images. To comply with regulations, the sensitive patient data must not leave the country the data is located in. Which data governance strategy will ensure compliance and protect patient privacy?
Answer: A
A company needs to monitor the performance of its ML systems by using a highly scalable AWS service. Which AWS service meets these requirements?
Answer: A
A financial institution is using Amazon Bedrock to develop an AI application. The application is hosted in a VPC. To meet regulatory compliance standards, the VPC is not allowed access to any internet traffic. Which AWS service or feature will meet these requirements?
Answer: A
AWS PrivateLink enables secure, private connectivity between Virtual Private Cloud (VPC) environments and AWS services without exposing traffic to the public internet
Source: Adapted from community discussion — jove
An AI practitioner is developing a prompt for an Amazon Titan model. The model is hosted on Amazon Bedrock. The AI practitioner is using the model to solve numerical reasoning challenges. The AI practitioner adds the following phrase to the end of the prompt: “Ask the model to show its work by explaining its reasoning step by step.” Which prompt engineering technique is the AI practitioner using?
Answer: A
Which AWS service makes foundation models (FMs) available to help users build and scale generative AI applications?
Answer: B
Amazon Bedrock is a fully managed service that provides access to a variety of high-performing foundation models from leading AI companies and Amazon itself. It offers a single API for accessing different foundation models, allowing for easy experimentation and integration into applications.
Source: Adapted from community discussion — jerry00218
A company is building a mobile app for users who have a visual impairment. The app must be able to hear what users say and provide voice responses. Which solution will meet these requirements?
Answer: A
A. Use a deep learning neural network to perform speech recognition. While C sounds feasible, it does not handle the input of the speeches
Source: Adapted from community discussion — chris_spencer
A company wants to enhance response quality for a large language model (LLM) for complex problem-solving tasks. The tasks require detailed reasoning and a step-by-step explanation process. Which prompt engineering technique meets these requirements?
Answer: D
Chain-of-thought (CoT) prompting is one of the oldest “chain of” methods for improving LLM performance – in particular in the context of queries or tasks that need complex, human-like reasoning to reach an answer.
Source: Adapted from community discussion — ajey255
A company wants to keep its foundation model (FM) relevant by using the most recent data. The company wants to implement a model training strategy that includes regular updates to the FM. Which solution meets these requirements?
Answer: B
Answer: B. Continuous pre-training To keep a foundation model (FM) updated with the most recent data on a regular basis, you need a training approach that continually integrates new information. Continuous pre-training fits this requirement because it periodically (or even continuously) retrains or fine-tunes the model with the latest data, ensuring relevance and improved performance. Here's why the other options are less suitable: A. Batch learning: Trains in large, discrete batches and may introduce significant delays between training cycles, potentially causing the model to become stale. C. Static training: Trains the model once and does not update it with new data, leading to outdated predictions. D. Latent training: Not a standard industry term or recognized strategy for regularly updating foundation models.
Source: Adapted from community discussion — jerry00218
Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page
AIF-C01 practice, question 31. 417 questions available.
Version 1.0.0. How we source questions