AIF-C01 Quick Quiz — 10 Questions

Question 1

A team is deploying a generative AI model for medical report generation. They must ensure patient data privacy and comply with HIPAA. Which AWS service feature is essential for de-identifying protected health information (PHI) before sending data to a foundation model?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Amazon Comprehend Medical. Amazon Comprehend Medical is the correct service because it is specifically designed to extract and de-identify protected health information (PHI) from unstructured medical text using natural language processing (NLP). It can detect entities such as patient names, dates, and medical record numbers, and then redact or replace them before the data is sent to a foundation model, ensuring HIPAA compliance.

Answer

AWS CloudHSM

Answer

Amazon Macie

Answer

AWS Key Management Service (AWS KMS)

Question 2

A developer is using the Amazon Bedrock Converse API to build a multi-turn conversational AI. They need to send a user message along with system instructions and previous conversation history. How should they structure the API request to include both system prompt and message history?

Accepted Answer

Include system prompt in the 'system' parameter and user/assistant messages in the 'messages' array. The Amazon Bedrock Converse API separates system prompts from the conversation history. System prompts are passed in the dedicated 'system' parameter, while user and assistant messages are placed in the 'messages' array. This design allows the model to distinguish persistent instructions from the ongoing dialogue, ensuring system-level guidance is not treated as part of the conversation context.

Answer

Include system prompt as a user message in the 'messages' array

Answer

Include system prompt as an assistant message in the 'messages' array

Answer

Include system prompt in the 'inferenceConfig' parameter

Question 3

A company uses Amazon Bedrock to run a question-answering system over a large internal knowledge base. They currently use a RAG approach with Titan Embeddings to index documents and a separate LLM for generation. The team notices that the retrieval often returns irrelevant chunks, causing the LLM to produce incorrect answers. Which action would MOST directly improve retrieval relevance?

Accepted Answer

Switch from Titan Embeddings to a more powerful embedding model like Cohere Embed on Bedrock. The core issue is that the retrieval step is returning irrelevant chunks, which directly undermines the RAG pipeline. Switching from Titan Embeddings to a more powerful embedding model like Cohere Embed on Bedrock improves the semantic quality of the vector representations, leading to more relevant document retrieval. This directly addresses the root cause of poor retrieval relevance, whereas other options focus on generation or chunking parameters that do not fix the embedding quality.

Answer

Add a system prompt instructing the LLM to only answer when confident

Answer

Reduce the chunk size of documents to 256 tokens

Answer

Increase the temperature of the LLM to 0.7

Question 4

A financial services company is deploying a generative AI chatbot to assist customers with account inquiries. The company wants to ensure the chatbot does not generate biased or harmful responses. Which combination of AWS services and practices should the company implement to monitor and mitigate these risks?

Accepted Answer

Use Amazon SageMaker Clarify to detect bias in model outputs and implement a human-in-the-loop workflow with Amazon A2I to review flagged responses.. Amazon SageMaker Clarify is specifically designed to detect bias in machine learning models and their outputs, while Amazon Augmented AI (A2I) enables a human-in-the-loop workflow to review flagged responses. This combination directly addresses the requirement to monitor and mitigate biased or harmful responses from a generative AI chatbot, ensuring responsible AI practices.

Answer

Configure the chatbot to use a pre-trained model from SageMaker JumpStart and disable logging to avoid storing sensitive customer data.

Answer

Use Amazon Rekognition to analyze chat logs for biased language and automatically block responses with a confidence score above 90%.

Answer

Deploy Amazon Lex with built-in sentiment analysis to detect negative customer emotions and automatically escalate to a human agent.

Question 5

A data science team wants to document and share their model's intended use, performance, and limitations with stakeholders. They also need to track the model's version and deployment history. Which TWO AWS services or features should they use?

Accepted Answer

Amazon SageMaker Model Cards. SageMaker Model Cards provide standardized documentation for transparency. SageMaker Model Registry tracks model versions, deployment stages, and metadata. SageMaker Pipelines is for ML workflows, not documentation or version tracking. SageMaker Studio is an IDE. SageMaker Clarify is for bias and explainability.

Answer

Amazon SageMaker Pipelines

Answer

Amazon SageMaker Clarify

Answer

Amazon SageMaker Studio

Question 6

A company uses Amazon Bedrock Agents to automate order processing. The agent needs to call an internal database to check inventory. Which component should be used to integrate the database query?

Accepted Answer

Action group. Bedrock Agents use action groups to define external tools or APIs. Each action group has an associated AWS Lambda function that performs the actual work (e.g., querying a database). The agent can call the action group via natural language instructions.

Answer

Knowledge base

Answer

Guardrail

Answer

Prompt template

Question 7

A developer wants to create an agent using Amazon Bedrock Agents that can call an external API to check inventory levels. What must be defined in the agent configuration to enable this API call?

Accepted Answer

An action group. Action groups define the set of actions (API calls) that an agent can perform. Each action group specifies the API schema and optionally a Lambda function for execution.

Answer

A knowledge base

Answer

A guardrail

Answer

A prompt template

Question 8

A company wants to use AWS services to process natural language text. Which TWO AWS services provide natural language processing (NLP) capabilities? (Select TWO.)

Accepted Answer

Amazon Comprehend. Amazon Comprehend (C) is correct because it is AWS's fully managed NLP service that uses machine learning to extract insights from text, including sentiment analysis, entity recognition, key phrase extraction, language detection, and topic modeling. Amazon Lex (E) is correct because it provides NLP capabilities for building conversational interfaces (chatbots and voice bots) using automatic speech recognition and natural language understanding to interpret user intent and slot values. Amazon Translate (A) is not marked correct because it performs language translation rather than general NLP analysis, even though it is a text-processing service. Amazon Rekognition (B) is not marked correct because it is a computer vision service for image and video analysis, not natural language text. Amazon Polly (D) is not marked correct because it is a text-to-speech service that converts written text into lifelike speech, which is speech synthesis rather than NLP understanding.

Answer

Amazon Translate

Answer

Amazon Rekognition

Answer

Amazon Polly

Question 9

A developer is building a RAG application on Amazon Bedrock. They notice that the model sometimes generates answers that are not supported by the retrieved documents. To reduce this, they want to enforce that the model only uses the provided context. Which Bedrock feature should they use?

Accepted Answer

Enable 'grounding' in Bedrock Guardrails. Amazon Bedrock Guardrails includes a contextual grounding check that evaluates whether a model's response is factually supported by the source context (the retrieved documents) and whether it is relevant to the user's query. By enabling grounding in Guardrails, the developer can configure thresholds that filter or flag responses with low grounding scores, directly reducing hallucinations. This is the purpose-built Bedrock feature for enforcing that answers stay within the provided context.

Answer

Increase the number of retrieved documents

Answer

Use a larger context window model

Answer

Adjust the temperature parameter to 0

Question 10

A data scientist needs to train a model in Amazon SageMaker using a dataset that contains personally identifiable information (PII). The company policy requires all data at rest to be encrypted with a customer-managed key. Which configuration meets this requirement?

Accepted Answer

Specify a KMS customer-managed key when creating the SageMaker training job and enable data encryption for the S3 bucket with the same key. Using a KMS customer-managed key (CMK) for SageMaker's EBS volumes and S3 buckets ensures encryption at rest with a key the customer controls. The other options either use AWS-managed keys, skip encryption, or are not applicable to SageMaker training jobs.

Answer

Enable default encryption for the S3 bucket using AWS-managed S3 keys (SSE-S3)

Answer

Encrypt the data before uploading to S3 using a client-side library

Answer

Use SageMaker's local mode and store data on the instance's ephemeral storage