Question 1

A fintech company is launching a GenAI-powered "Spending Analyzer" feature. The application uses a Large Language Model (LLM) on Amazon Bedrock to explain transaction history to users. The project has two critical governance requirements:Compliance: The model must strictly refuse to answer any questions related to "Tax Advice" or "Legal Liability," as the company is not licensed to provide these services.Agility: The non-technical Product Team needs the ability to update the "Persona" and "Output Format" (e.g., switching from paragraphs to bullet points) of the analyzer weekly without requiring the engineering team to deploy new application code.Which combination of AWS GenAI features should the developer implement to meet these requirements? (Choose two)

Options :

A : Fine-tune the Foundation Model using Amazon SageMaker JumpStart on a dataset of "Refusal" examples. Train the model to recognize tax-related questions and output a standard disclaimer.

B : Implement Amazon Bedrock Prompt Management. Create a parameterized prompt template that defines the System Prompt (Persona) and output structure. Grant the Product Team permissions to iterate, test, and version the prompt within the Bedrock console.

C : Implement a post-processing AWS Lambda function. Use a keyword list (e.g., "tax", "audit", "lawyer") to scan the generated text. If a restricted keyword is found, overwrite the response with a hardcoded error message.

D : Use AWS Systems Manager Parameter Store to hold the System Prompt string. Update the backend Lambda function to fetch the latest prompt version on every invocation. Give the Product Team access to the Systems Manager console to edit the string.

E : Create an Amazon Bedrock Guardrail. Configure a "Denied Topics" policy that explicitly defines "Tax Advice" and "Legal Advice" with description examples. Attach this guardrail to the model invocation to intercept and block restricted queries.

Answer: B,E

Question 2

A marketing analytics company generates monthly reports that include AI-generated summaries of customer feedback. They have 10,000 customer feedback entries to summarize each month. The summaries are not time-sensitive and can be processed overnight. The team wants to optimize costs compared to processing requests one-by-one in real-time.Which processing approach should the developer use to reduce costs?

Options :

A : Invoke the foundation model in real-time for each customer feedback entry as soon as it arrives

B : Use provisioned throughput to guarantee capacity for all 10,000 requests

C : Use batch processing to send multiple requests together and process them during off-peak hours

D : Enable auto-scaling to handle the large burst of requests

Answer: C

Question 3

A news aggregator uses a RAG architecture with Amazon OpenSearch Service (Provisioned) as the vector store. The system ingests breaking news in real-time, performing thousands of vector insertions per minute.Users are reporting that the "Related Articles" search is becoming increasingly slow (high latency) during these ingestion spikes. The OpenSearch cluster metrics show high CPU utilization and high JVM memory pressure.The index is configured with the standard settings for k-NN search.Which index configuration change should the developer apply to improve search performance under heavy ingestion load?

Options :

A : Change the vector data type from float32 to binary to reduce the storage footprint.

B : Switch the index engine from nmslib to faiss and enable the ivf (Inverted File) algorithm.

C : Enable the "Force Merge" operation to run automatically every minute to reduce the number of segments in the index.

D : Increase the refresh_interval setting of the OpenSearch index (e.g., from 1s to 30s or 60s).

Answer: D

Question 4

A content moderation system needs to identify specific grammatical patterns in user-generated text, such as detecting imperative sentences (commands) or questions. The team wants to understand the grammatical structure and parts of speech (nouns, verbs, adjectives) in text before making moderation decisions.Which Amazon Comprehend feature should they use?

Options :

A : Sentiment analysis

B : Syntax analysis (part-of-speech tagging)

C : Entity recognition

D : Key phrase extraction

Answer: B

Question 5

An aerospace engineering firm is developing a RAG (Retrieval Augmented Generation) application that allows mechanics to query thousands of technical maintenance manuals. To meet strict aviation safety regulations, the application requires full traceability for every answer generated:Source Attribution: Every response generated by the model must explicitly cite the specific manual ID and version number it originated from.Data Governance: All valid maintenance datasets must be centrally registered and version-controlled.Auditability: Access to the underlying data files during the retrieval process must be logged for compliance audits.Which implementation strategy satisfies these requirements?

Options :

A : Register the maintenance manuals in the AWS Glue Data Catalog. During the ingestion process, attach metadata tags (Manual ID, Version) to the document chunks stored in the vector database and configure the application to return these tags with the response. Enable AWS CloudTrail to log the data access API calls.

B : Ingest the manuals into Amazon Kendra and enable the "Document relevance tuning" feature to prioritize recent versions. Use Amazon CloudWatch Logs to capture the full text of every query and response for the audit team to manually verify the sources later.

C : Use Amazon S3 Object Tagging to label each PDF with its Manual ID. Configure the Amazon Bedrock model to read these tags directly from S3 during inference. Use Amazon S3 Server Access Logs to track the requests made by the model.

D : Store the manuals in Amazon DynamoDB with a Global Secondary Index (GSI) for the Manual ID. Use Amazon Macie to discover and classify the technical data. Configure the GenAI application to query DynamoDB Streams to retrieve the source lineage.

Answer: A

Confidently Practice Online with Free AIP-C01 Exam Cram

Buying Options: