Question 1

An e-commerce company uses an Amazon Bedrock Agent to handle product returns. The agent has access to two tools: GetOrderDetails and ProcessRefund.During testing, the agent fails to process refunds for orders older than 30 days. Instead of calling the ProcessRefund tool, the agent simply apologizes to the user.The developer suspects the agent is correctly identifying the return policy date limit but needs to verify the specific logic used by the agent to reach this decision.Which troubleshooting step provides the necessary visibility?

Options :

A : Check CloudWatch Metrics. Look at the Invocations and Errors metrics for the ProcessRefund Lambda function. If the count is zero, it confirms the tool was never called.

B : Review CloudTrail Logs. Search for the InvokeModel events. Download the raw request payload to see if the system prompt includes the "30-day return policy" instruction.

C : Analyze the Agent Trace. Invoke the agent with enableTrace=true. Inspect the orchestrationTrace to view the "Observation" step where the agent received the order date from GetOrderDetails and the subsequent "Rationale" step where it reasoned that the date exceeded the 30-day policy.

D : Use Amazon Bedrock Model Evaluation. Run an evaluation job using the "Tool Usage Accuracy" metric to see a statistical percentage of how often the agent fails to call the tool.

Answer: C

Question 2

A financial services firm processes thousands of unstructured PDF earnings reports daily. The engineering team uses Anthropic Claude 4.5 Sonnet on Amazon Bedrock to extract specific Key Performance Indicators (KPIs) and populate a downstream SQL database.Users have reported that while the model handles narrative text well, it consistently hallucinates values when processing financial tables that span multiple pages or contain complex nested headers. The raw text ingested from the OCR pipeline often arrives with broken formatting, missing whitespace, and merged columns.Which strategy should the GenAI Developer implement to enhance the input data quality and resolve the extraction errors?

Options :

A : Use an AWS Lambda function to apply a uniform truncation to all input documents, limiting them to the first 2,000 tokens to ensure the model focuses only on the high-level summary tables usually found at the beginning of reports.

B : Increase the temperature parameter of the Claude 4.5 Sonnet model to 0.7 to encourage the model to be more creative in interpreting the broken table structures.

C : Introduce a pre-processing step using the Amazon Bedrock ConverseAPI with a lightweight model like Anthropic Claude 3.5 Haiku. Prompt this model to rewrite the raw OCR output into valid Markdown tables, then pass this cleaned, structured text to Claude 4.5 Sonnet for the final KPI extraction.

D : Replace the OCR pipeline with Amazon Textract's raw text detection. Directly concatenate the raw LINE block outputs into a JSON object and feed this massive JSON structure into Claude 4.5 Sonnet without any further serialization.

Answer: C

Question 3

A healthcare company stores patient intake forms, insurance documents, and medical records as PDF files in multiple Amazon S3 buckets. Before building a GenAI document summarization system, the security team needs to identify which S3 buckets contain sensitive PII (like Social Security numbers, patient names, and medical record numbers) to ensure proper access controls are in place.Which AWS service should the security team use to automatically discover and classify sensitive data across their S3 buckets?

Options :

A : Amazon Inspector

B : Amazon Macie

C : Amazon Comprehend

D : AWS CloudTrail

Answer: B

Question 4

A large financial services enterprise is building a centralized platform to allow internal development teams to consume Foundation Models (FMs) from Amazon Bedrock. To ensure strict compliance and governance, the organization requires a "GenAI Gateway" architecture.The architecture must meet the following requirements:Prevent "Shadow AI" by forcing all internal applications to route requests through a single control point that logs every prompt and response for auditing.Automate the testing of prompt templates. Whenever a prompt engineer updates a standard system prompt, it must be automatically evaluated for toxicity and accuracy before being made available to applications.Ensure that PII is automatically redacted from prompts before they are sent to the model provider.Which combination of actions should you implement to achieve this?

Options :

A : Grant all internal application roles direct IAM permissions to bedrock:InvokeModel. Enable AWS CloudTrail data events for Amazon Bedrock to capture the request payloads and response bodies for auditing purposes.

B : Use Amazon Inspector within the CI/CD pipeline to scan the weights of the Amazon Bedrock base models for vulnerabilities and malware before approving them for use in the production environment.

C : Implement AWS AppSync with a direct data source to Amazon Bedrock. Use VTL resolvers to hardcode the system prompts within the API definition, ensuring that developers cannot modify them without redeploying the API.

D : Develop a centralized REST API using Amazon API Gateway and AWS Lambda. Configure the Lambda function to act as an abstraction layer that intercepts requests, uses Amazon Comprehend to detect and redact PII, logs the transaction to Amazon CloudWatch Logs, and then invokes Amazon Bedrock.

E : Create an AWS CodePipeline for prompt versioning. Include an AWS CodeBuild stage that runs an automated evaluation script (using a library like Ragas or specific Bedrock evaluations) against the new prompt candidate. Configure the pipeline to fail and rollback if the toxicity score exceeds a defined threshold.

Answer: D,E

Question 5

A healthcare technology company is building a patient inquiry chatbot using Amazon Bedrock. Before logging conversation transcripts for quality assurance, they must ensure that all personally identifiable information (names, phone numbers, addresses, medical record numbers) is detected and redacted to comply with HIPAA privacy requirements.Which combination of AWS services should the developer use to detect and redact PII from conversation logs?

Options :

A : Use AWS CloudTrail to automatically redact PII from all logs

B : Use Amazon Textract to extract PII from documents, then delete the documents

C : Use Amazon Comprehend to detect PII entities, then use Amazon Bedrock Guardrails to redact them from logs

D : Use Amazon Macie to scan conversation logs stored in S3

Answer: C

Free AIP-C01 Mock Exam – Practice Online Confidently

Buying Options: