AIF-C01 Practice Test 14 — 15 Questions

Question 1

A developer is using Amazon Bedrock Agents to build a multi-step reasoning workflow. The agent needs to query an external REST API to fetch data. What must the developer define in the agent configuration?

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

Accepted Answer

An action group with the API schema and a Lambda function. Action groups allow agents to invoke external APIs (via AWS Lambda) or knowledge bases. The developer must define an action group that describes the API operations the agent can call, along with the Lambda function that implements the API integration.

Answer

A prompt template with the API endpoint URL

Answer

A knowledge base with the API schema

Answer

A guardrail to filter API responses

Question 2

Refer to the exhibit. An IAM policy is attached to a role used by an Amazon SageMaker notebook instance. The notebook instance attempts to upload a model artifact to the S3 bucket 'my-bucket' without specifying server-side encryption. What will happen?

Accepted Answer

The upload fails with an access denied error. The IAM policy attached to the SageMaker role includes a condition that denies s3:PutObject unless the request includes the x-amz-server-side-encryption header with a value of 'AES256'. Since the notebook instance attempts to upload without specifying server-side encryption, the condition is not met, and the request is denied with an access denied error. S3 default bucket encryption does not override explicit IAM policy conditions that require encryption headers in the request.

Answer

The upload succeeds because S3 automatically encrypts objects at rest

Answer

The upload fails because the policy does not allow PutObject without encryption

Answer

The upload succeeds because the bucket has default encryption enabled

Question 3

A company is developing an AI system for resume screening. They want to ensure fairness and reduce bias. Which THREE steps should they take in accordance with the NIST AI Risk Management Framework and AWS responsible AI principles?

Accepted Answer

Establish a governance process for regular auditing and human review of decisions. The NIST AI Risk Management Framework emphasizes measuring bias, ensuring diverse data, and establishing governance. Removing sensitive features alone is insufficient due to proxy correlations. Relying solely on accuracy ignores fairness. The three correct steps cover measurement, data diversity, and governance.

Answer

Optimize the model solely for overall accuracy

Answer

Remove all sensitive attributes (e.g., gender, race) from the dataset

Question 4

A data scientist is training a binary classification model to predict customer churn. The dataset has 10,000 records with 9,500 non-churners and 500 churners. After training a logistic regression model, the model achieves 95% accuracy on the test set. However, the business team reports that the model is not useful because it predicts almost all customers as non-churners. Which metric should the data scientist use to evaluate the model's performance in this scenario?

Accepted Answer

Recall. (Recall) is correct because in this highly imbalanced dataset (95% non-churners vs 5% churners), the model's 95% accuracy is misleading—it can achieve this by simply predicting the majority class (non-churner) for all samples. Recall measures the proportion of actual churners correctly identified (True Positives / (True Positives + False Negatives)), directly addressing the business need to detect churn. A high recall ensures the model captures most churners, even at the cost of some false positives.

Answer

Accuracy

Answer

R-squared

Answer

Precision

Question 5

A developer is using Amazon Bedrock to generate product descriptions. The developer notices that the model sometimes outputs descriptions that contradict the provided product specifications. Which parameter adjustment would MOST directly reduce factual inconsistencies?

Accepted Answer

Decrease temperature to a value close to 0. Decreasing temperature to a value close to 0 makes the model more deterministic and less creative, which reduces the likelihood of generating random or contradictory content. In Amazon Bedrock, temperature controls the randomness of token selection; lower values cause the model to choose the most probable tokens, aligning outputs more closely with the provided product specifications and minimizing factual inconsistencies.

Answer

Increase maxTokens to allow longer descriptions

Answer

Increase topP to 1.0

Answer

Set topK to a higher value

Question 6

A data scientist is prototyping a text generation application using Amazon Bedrock. They want to quickly test different foundation models with various prompts and parameters without writing any code. Which AWS service or feature should they use?

Accepted Answer

Amazon Bedrock Playground. Amazon Bedrock Playground is a no-code, interactive environment within the Amazon Bedrock console that allows users to experiment with different foundation models, adjust inference parameters (like temperature, top-p, and max tokens), and test prompts in real time. It is specifically designed for rapid prototyping and comparison of models without writing any code. This directly matches the data scientist's requirement to quickly test various models and prompts without coding.

Answer

Amazon Comprehend console

Answer

AWS Lambda with the Bedrock SDK

Answer

Amazon SageMaker Studio Notebooks

Question 7

Which TWO AWS services can be used to build a chatbot that responds to customer inquiries using a company's documentation as source? (Select two.)

Accepted Answer

Amazon Bedrock with RAG. Amazon Bedrock with RAG (A) is correct because it lets you build generative AI chatbots that retrieve relevant passages from your company documentation (stored in services like Amazon S3 or OpenSearch) and pass them to a foundation model as context, so answers are grounded in the source material. Amazon Q Business (C) is correct because it is a fully managed generative AI assistant that natively connects to enterprise data sources (S3, SharePoint, Confluence, etc.), indexes the documentation, and answers customer inquiries with citations from that content. Amazon Polly (B) is only a text-to-speech service and cannot retrieve or reason over documentation, Amazon Transcribe (D) only converts speech to text, and Amazon Lex (E) builds conversational interfaces/intents but does not itself perform retrieval-augmented generation over a company's documentation.

Answer

Amazon Polly

Answer

Amazon Transcribe

Answer

Amazon Lex

Question 8

Which TWO actions are most aligned with responsible AI practices when deploying a model that makes decisions affecting individuals? (Choose 2)

Accepted Answer

Continuously monitor the model for fairness metrics. Option B is correct because responsible AI requires ongoing monitoring of deployed models for fairness metrics (such as demographic parity, equalized odds, or disparate impact) to detect and mitigate bias that can emerge or drift after deployment. Option E is correct because providing meaningful explanations for model decisions supports transparency and accountability, enabling affected individuals to understand and potentially contest decisions, which aligns with principles like explainability and due process. Option A is incorrect because indiscriminate data collection without quality checks introduces noise, bias, and privacy risks rather than improving responsible AI. Option C is incorrect because a homogeneous development team increases the risk of blind spots and systemic bias, whereas diverse teams better surface fairness concerns. Option D is incorrect because maximizing model complexity for accuracy alone ignores interpretability, fairness, and other responsible AI trade-offs.

Answer

Collect as much data as possible without quality checks

Answer

Ensure the development team is homogeneous to avoid conflicts

Answer

Use the most complex model available for maximum accuracy

Question 9

A company uses Amazon Bedrock Agents to build an agent that interacts with users through a chat interface. The agent is configured with a knowledge base containing product documentation. Sometimes the agent fails to answer simple questions like 'What is your return policy?' and instead says it cannot find the answer. The knowledge base does contain the return policy. What is the most likely reason?

Accepted Answer

Simplify and clarify the agent's instruction prompt to emphasize knowledge base usage. The agent's instruction prompt might be too complex or not explicitly directing the agent to use the knowledge base. Simplifying the prompt to clearly instruct the agent to first search the knowledge base can resolve the issue. Increasing timeout or adding more data is unnecessary. A stronger model may help but is not the root cause.

Answer

Increase the agent's maximum timeout for processing

Answer

Use a more powerful foundation model for reasoning

Answer

Add more documents to the knowledge base

Question 10

A data scientist needs to predict house prices based on features like square footage, number of bedrooms, and location. Which type of machine learning is most appropriate for this task?

Accepted Answer

Regression. Regression is the correct choice because the task involves predicting a continuous numerical value (house price) based on input features. Unlike classification, which predicts discrete categories, regression models the relationship between independent variables and a continuous target, making it ideal for price prediction.

Answer

Classification

Answer

Reinforcement learning

Answer

Clustering

Question 11

A data scientist is building a RAG application using Amazon Bedrock Knowledge Bases. The team requires that responses only use information from the uploaded documents and reject queries that are not related to the documents. Which Bedrock feature should be used to enforce this?

Accepted Answer

Bedrock Guardrails. Amazon Bedrock Guardrails lets you define denied topics, content filters, and contextual grounding checks that constrain what a model can say. For a RAG app that must answer only from uploaded documents and reject off-topic queries, Guardrails' contextual grounding and denied-topics policies enforce that boundary at inference time. This is the Bedrock feature purpose-built for controlling model responses.

Answer

Bedrock Knowledge Bases

Answer

Bedrock Agents

Answer

Bedrock Model Evaluation

Question 12

Which TWO actions are best practices for reducing hallucinations in generative AI models? (Choose 2)

Accepted Answer

Use retrieval-augmented generation (RAG). Option C, retrieval-augmented generation (RAG), is correct because it grounds the model's responses in externally retrieved, authoritative documents at inference time, so the model cites or conditions on real source content rather than relying solely on parametric memory, which measurably reduces fabricated facts. Option E, prompt engineering with clear instructions and constraints, is correct because explicit directives such as "answer only from the provided context," "say 'I don't know' if unsupported," and output-format constraints steer the model away from speculative generation and make hallucinations easier to detect. Option A, increasing model size, is not a reliable fix: larger models can be more fluent and confident while still hallucinating, and scale alone does not guarantee factual grounding. Option B, fine-tuning on proprietary data, mainly adapts style, format, and domain vocabulary and can even increase confident fabrication on facts not present in the tuning set, so it is not a primary hallucination-reduction best practice. Option D, using a smaller model, is also not a best practice for this goal, since reduced capacity generally lowers factual accuracy and reasoning rather than improving truthfulness.

Answer

Increase the model size

Answer

Fine-tune the model on proprietary data

Answer

Use a smaller model to limit complexity

Question 13

A data science team is using Amazon Bedrock to generate synthetic data for training a new model. They need to ensure the generated data is diverse and covers edge cases. Which THREE parameters should they adjust to maximize diversity? (Select THREE.)

Accepted Answer

Increase the top-p value to 0.9. Option E (increase the temperature) is correct because temperature scales the logits before softmax, flattening the probability distribution so lower-probability tokens are sampled more often, which directly increases output diversity and helps surface edge cases. Option A (increase top-p to 0.9) is correct because top-p (nucleus) sampling retains the smallest set of tokens whose cumulative probability reaches 0.9, keeping a broad candidate pool instead of truncating to only the most likely tokens. Option B (increase top-k to 50) is correct because top-k sampling restricts sampling to the 50 highest-probability tokens, and a larger k widens that pool, allowing more varied token choices than a small k. Option C (decrease top-p to 0.1) is not correct because a narrow nucleus of only the top ~10% cumulative probability makes generation more deterministic and less diverse. Option D (set a fixed seed) is not correct because a fixed seed makes sampling reproducible, not more diverse, and can actually reduce variation across runs.

Answer

Decrease the top-p value to 0.1

Answer

Set the seed to a fixed value

Question 14

A developer is using the Amazon Bedrock InvokeModel API with streaming enabled. They want to process partial results as they arrive. Which THREE steps are necessary to implement streaming correctly? (Select THREE.)

Accepted Answer

Use the InvokeModelWithResponseStream API operation to request a streaming response.. The correct options are B, D, and E. Option B is required because InvokeModelWithResponseStream is the specific Bedrock API operation that returns a stream of response chunks (via the responseStream event stream) rather than a single blocking response, which is exactly what the developer needs to process partial results as they arrive. Option D is required because the streaming response is delivered as an event stream of typed events such as chunk and modelStreamErrorException, so the client must iterate over the stream and decode each chunk's bytes (for example, base64-decoded JSON delta text) to consume partial output incrementally. Option E is required because streaming responses can terminate with in-stream error events and the connection can drop mid-stream, so the implementation must handle these exceptions and read the stream to completion to avoid truncated output. Options A and C are not part of the necessary streaming implementation: they describe non-streaming or unrelated behaviors and are not marked correct.

Answer

Call the standard InvokeModel API and wait for the entire JSON response before processing partial results.

Answer

Enable raw HTTP/2 callbacks on the Bedrock client to automatically invoke a callback for each partial result.

Question 15

A team is deploying a sentiment analysis application using Amazon Bedrock. They need to ensure the model returns only 'positive', 'negative', or 'neutral'. Which prompt engineering technique is BEST suited for this requirement?

Accepted Answer

Include an instruction like 'Classify the sentiment as one of: positive, negative, neutral. Output only that word.'. It directly constrains the model's output format using a clear, explicit instruction. This is the most reliable prompt engineering technique for enforcing a strict set of allowed labels, as it leverages the model's instruction-following capability without relying on reasoning chains or external filtering.

Answer

Use a chain-of-thought prompt to reason about sentiment

Answer

Provide few-shot examples of the three labels in the prompt

Answer

Use a Bedrock Guardrail to block any response not matching the three labels