AIP-C01AWS Certified Generative AI Developer – Professional
Progress0/124
| # | Question | Time | |
|---|---|---|---|
| 1 | A company plans to establish an annual customer rewards program. The rewards customers earn differ according to various parameters, including the categories of items they order and the customers' purchase history. The company requires a generative AI (GenAI) solution that uses three Amazon Bedrock agents to assist customers while they browse an online catalog. The agents must use knowledge bases and action groups to manage the search, recommendation, and order modules. The modules must run sequentially. An AWS Lambda function must calculate estimated rewards for every recommended item. The solution must offer graceful degradation during service disruptions. Which solution meets these requirements with the MOST operational efficiency? | – | |
| 2 | A company uses an AWS Organizations organization with all features enabled to manage multiple AWS accounts. Employees use Amazon Bedrock in multiple accounts. The company must prevent particular topics and proprietary information from being included in prompts submitted to Amazon Bedrock models. The company must ensure that employees can use only approved Amazon Bedrock models. The company centrally administers IAM roles for employees. Which combination of solutions will satisfy these requirements? | – | |
| 3 | A company is developing a generative AI (GenAI) application that generates content from a range of internal and external data sources. The company needs to ensure that all generated output is fully traceable. The application must support registering data sources and allow metadata tagging to attribute content to its original source. It must also retain audit logs of data access and usage across the entire pipeline. Which solution meets these requirements? | – | |
| 4 | A company is developing a generative AI (GenAI) application that uses Amazon Bedrock APIs to process complex customer inquiries. During periods of peak use, the application has intermittent API timeouts that result in issues such as broken response chunks and delayed data delivery. The application has difficulty ensuring prompts stay within token limits when processing complex customer inquiries of different lengths. Users have reported truncated inputs and incomplete responses. The company has also identified foundation model (FM) invocation failures. The company requires a retry strategy that automatically manages transient service errors and avoids overwhelming Amazon Bedrock during peak usage periods. The strategy must adapt to changing service availability and support response streaming and token-aware request handling. Which solution meets these requirements? | – | |
| 5 | An enterprise application uses an Amazon Bedrock foundation model (FM) to process and analyze technical documents of 50 to 200 pages. Users experience inconsistent responses and truncated outputs when processing documents that exceed the FM's context-window limits. Which solution will solve this problem? | – | |
| 6 | A retail company uses Amazon Bedrock to build a customer service AI assistant. Analysis indicates that 70% of customer inquiries are simple product questions that a smaller model can handle effectively. However, 30% of inquiries are complex return-policy questions requiring advanced reasoning. The company wants to implement a cost-effective model-selection framework that automatically routes customer inquiries to appropriate models according to inquiry complexity. The framework must preserve high customer satisfaction and minimize response latency. Which solution meets these requirements with the LEAST implementation effort? | – | |
| 7 | A company uses AWS Lambda functions to create an AI agent solution. A GenAI developer must configure a Model Context Protocol (MCP) server that accesses user information. The GenAI developer must also configure the AI agent to use the new MCP server. The GenAI developer must ensure that only authorized users can access the MCP server. Which solution meets these requirements? | – | |
| 8 | A GenAI developer is developing a Retrieval Augmented Generation (RAG)-based customer-support application that uses Amazon Bedrock foundation models (FMs). The application must process 50 GB of historical customer conversations stored as JSON files in an Amazon S3 bucket. It must use the processed data as its retrieval corpus. The application's data-processing workflow must extract relevant data from customer-support documents, remove customer personally identifiable information (PII), and generate embeddings for vector storage. The workflow must be cost-effective and complete within 4 hours. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 9 | A company uses Amazon Bedrock to create technical content for customers. The company has recently seen a surge in hallucinated outputs when its model produces summaries of lengthy technical documents. The outputs contain incorrect or invented details. The current solution uses a large foundation model (FM) with a basic one-shot prompt that supplies the complete document in one input. The company needs a solution that reduces hallucinations and satisfies factual-accuracy objectives. The solution must process more than 1,000 documents per hour and provide summaries within 3 seconds for each document. Which combination of solutions meets these requirements? | – | |
| 10 | A company upgraded its Amazon Bedrock-powered foundation model (FM) that supports a multilingual customer service assistant. Following the upgrade, the assistant showed inconsistent behavior between languages. It started producing different responses in some languages for identical questions. The company needs a solution to identify and remediate similar issues in future updates. The evaluation must: Which solution meets these requirements? | – | |
| 11 | A large ecommerce company has deployed a foundation model (FM) to create product descriptions. The company’s engineering team uses Amazon CloudWatch to monitor technical metrics such as token usage, latency, and error rates. Its marketing team tracks business metrics, including conversion rates and revenue impact, in separate systems. The company requires a unified observability solution that correlates technical performance with business outcomes. The solution must automatically alert stakeholders when operational metrics show degradation. It must also deliver comprehensive visibility across both technical and business metrics. Which solution meets these requirements? | – | |
| 12 | A financial services company is building a Retrieval Augmented Generation (RAG) application to help investment analysts query complex financial relationships spanning multiple investment vehicles, market sectors, and regulatory environments. The dataset includes highly interconnected entities with multi-hop relationships. Analysts must be able to review these relationships holistically to deliver accurate investment guidance. The application must provide comprehensive answers that include indirect relationships among financial entities. The application must return responses in under 3 seconds. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 13 | A company uses Amazon Bedrock to build an AI-powered application with a foundation model (FM) that supports cross-Region inference and provisioned throughput. The application must provide consistently low latency to users in Europe and North America. It must also comply with data-residency regulations requiring European user data to stay in Europe-based AWS Regions. During testing, the application has service degradation when Regional traffic spikes reach service quotas. The company requires a solution that preserves application resilience while minimizing operational complexity. Which solution meets these requirements? | – | |
| 14 | A company is developing a legal-research AI assistant that uses Amazon Bedrock with an Anthropic Claude foundation model (FM). The AI assistant must retrieve highly relevant case-law documents to augment the FM’s responses. It must recognize semantic relationships among legal concepts, specific legal terminology, and citations. The AI assistant must operate quickly and return precise results. Which solution meets these requirements? | – | |
| 15 | A company is developing a canary deployment strategy for a payment-processing API. The system must support automated, gradual traffic shifting among multiple Amazon Bedrock models based on real-time inference metrics, historical traffic patterns, and service health. The solution must be able to progressively increase traffic to new model versions. It must increase traffic when metrics stay healthy and reduce traffic when performance degrades below acceptable thresholds. The company needs comprehensive monitoring of inference latency and error rates throughout the deployment phase. The company must also be able to stop deployments and roll back to a previous model version without manual intervention. Which solution meets these requirements? | – | |
| 16 | A company operates a recommendation system whose applications run on Amazon EC2 instances. The applications make API calls to Amazon Bedrock foundation models (FMs) to analyze customer behavior and produce personalized product recommendations. The system is having intermittent problems. Some recommendations fail to align with customer preferences. The company requires an observability solution that monitors operational metrics and identifies patterns of operational performance degradation against established baselines. The solution must also produce alerts containing correlation data within 10 minutes when FM behavior departs from expected patterns. Which solution meets these requirements? | – | |
| 17 | A company uses Amazon Bedrock to build an AI assistant that provides customer support. Analysis indicates that 40% of customer queries use different phrasing or wording to ask the same questions. The company needs a solution that reduces redundant model calls, ensures semantically equivalent questions receive consistent answers, and provides low latency. Which solution meets these requirements? | – | |
| 18 | A medical company is developing a generative AI (GenAI) application that uses RAG to deliver evidence-based medical information. The application uses Amazon OpenSearch Service to retrieve vector embeddings. Users report that searches often miss results containing exact medical terms and acronyms, while returning too many semantically similar but irrelevant documents. The company must improve retrieval quality while keeping end-user latency low, even as the document collection scales to millions of documents. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 19 | A company is developing an API for a generative AI (GenAI) application that uses a foundation model (FM) hosted on a managed model service. The API must stream responses to lower latency, enforce token limits to control compute resource usage, and implement retry logic for model timeouts and partial responses. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 20 | A company is building a workflow to review customer-facing communications before it sends them. The company uses a predefined message template to generate the communications and stores the communications in an Amazon S3 bucket. The workflow must extract a specific portion of the template and send it to an Amazon Bedrock model. The workflow must save model responses back to the original S3 bucket. Which solution meets these requirements? | – | |
| 21 | An e-commerce company is building an internal platform for developing generative AI applications with Amazon Bedrock foundation models (FMs). Developers must choose models based on evaluations aligned with e-commerce use cases. The platform must show accuracy metrics for text generation and summarization in dashboards. The company has custom e-commerce datasets to use as standardized evaluation inputs. Which combination of steps meets these requirements with the LEAST operational overhead? | – | |
| 22 | A financial services company must build a document-analysis system using Amazon Bedrock to process quarterly reports. The system must analyze financial data, perform sentiment analysis, and validate compliance across batches of reports. Each batch contains 5 reports. Each report requires multiple foundation model (FM) calls. The solution must complete the analysis within 10 seconds for every batch. The current sequential processing takes 45 seconds for each batch. Which solution will satisfy these requirements? | – | |
| 23 | A company is developing an AI advisory application with Amazon Bedrock that will provide recommendations to customers. The company requires the application to explain its reasoning and cite specific data sources. It must retrieve information from company data sources and present step-by-step reasoning for its recommendations. It must also connect data claims to source documents and keep response latency below 3 seconds. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 24 | A specialty coffee company has a mobile app that uses Amazon Bedrock and a three-stage prompt chain to generate personalized coffee roast profiles. The prompt chain converts user inputs into structured metadata, retrieves relevant coffee-roast logs, and produces a personalized roast recommendation for each customer. Users across multiple AWS Regions report inconsistent roast recommendations for identical inputs, slow inference in the retrieval step, and unsafe recommendations, such as brewing at excessively high temperatures. The company must improve output stability for repeated inputs, application performance, and the safety of the application's outputs. The updated solution must ensure 99.5% output consistency for identical inputs and inference latency of less than 1 second. The solution must also block unsafe or hallucinated recommendations by using validated safety controls. Which solution will meet these requirements? | – | |
| 25 | A media company is releasing a platform that enables thousands of users each hour to upload images and text content. The platform uses Amazon Bedrock to process uploaded content and generate creative compositions. The company requires a solution that ensures the platform neither processes nor produces inappropriate content. The platform must not reveal personally identifiable information (PII) in the compositions. The solution must integrate with the company’s existing Amazon S3 storage workflow. Which solution meets these requirements with the LEAST infrastructure-management overhead? | – | |
| 26 | A university has recently digitized a collection of archival documents, academic journals, and manuscripts. The university keeps the digital files in an AWS Lake Formation data lake. The university employs a GenAI developer to build a solution that lets users search the digital files with text queries. The solution must return journal abstracts that are semantically similar to a user's query. Users must be able to search the digitized collection using text and metadata associated with the journal abstracts. The digitized-file metadata contains no keywords. The solution must match similar abstracts to each other based on the similarity of their text. The data lake contains fewer than 1 million files. Which solution will satisfy these requirements with the LEAST operational overhead? | – | |
| 27 | A company is designing a solution that uses foundation models (FMs) to support multiple AI workloads. Some FMs must be invoked on demand in real time. Other FMs need consistent, high-throughput access for batch processing. The solution must support hybrid deployment patterns and run workloads across cloud and on-premises infrastructure to meet data residency and compliance requirements. Which combination of steps meets these requirements? | – | |
| 28 | An ecommerce company runs a global product recommendation system that must switch among multiple foundation models (FMs) in Amazon Bedrock based on regulations, cost optimization, and performance requirements. The company must enforce custom controls based on proprietary business logic, including dynamic cost thresholds, AWS Region-specific compliance rules, and real-time A/B testing across multiple FMs. The system must be capable of switching between FMs without deploying new code. It must route user requests according to complex rules that include user tier, transaction value, regulatory zone, and real-time cost metrics that change hourly and need immediate propagation across thousands of concurrent requests. Which solution meets these requirements? | – | |
| 29 | A healthcare company uses Amazon Bedrock to deploy an application that produces summaries of clinical documents. The application has inconsistent response quality, including occasional factual hallucinations. Monthly costs are 40% higher than the company projected. A GenAI developer must implement a near-real-time monitoring solution that detects hallucinations, identifies abnormal token consumption, and provides early warnings for cost anomalies. The solution must involve minimal custom development and maintenance overhead. Which solution meets these requirements? | – | |
| 30 | A company is developing a serverless application that uses AWS Lambda functions to help students worldwide summarize notes. The application uses Anthropic Claude through Amazon Bedrock. The company has noticed that most traffic occurs during evening hours in each time zone. Users report throttling errors at peak usage times in their respective time zones. The company must resolve the throttling issues while ensuring the application operates continuously. The solution must preserve application performance quality and must not incur a fixed hourly cost during periods of low traffic. Which solution meets these requirements? | – | |
| 31 | A financial services company plans to use Amazon Bedrock foundation models (FMs) to analyze call center recordings. After calls end, the call center stores the recordings as MP3 files in an Amazon S3 bucket. The company must generate summaries and sentiment analysis for the recordings in a structured format as soon as new files are created. The recordings are 20 MB on average. Which combination of solutions will satisfy these requirements? | – | |
| 32 | A company is building a new AI-powered application that must integrate with several specialized tools. The tools currently operate as Model Context Protocol (MCP) servers on developers’ local machines and retain no state between invocations. The company intends to deploy each MCP server as an AWS Lambda function to support the production application. The solution must be reachable by both internal applications and authorized third-party partners, and it must enforce strict authentication and authorization controls. Which additional steps will satisfy these requirements with the LEAST operational overhead? | – | |
| 33 | An ecommerce company is building a generative AI (GenAI) solution that uses Amazon Bedrock with Anthropic Claude to recommend products to customers. Customers report that some recommended products are not available for sale on the website or are not relevant to the customer. Customers also report that the solution takes a long time to generate certain recommendations. The company investigates the issues and determines that most interactions between customers and the product recommendation solution are unique. The company confirms that the solution recommends products that are not in the company's product catalog. The company must resolve these issues. Which solution will meet this requirement? | – | |
| 34 | A company is building a generative AI (GenAI) application using Amazon Bedrock. The application will analyze patterns and relationships in the company’s data. It will process millions of new data points each day across AWS Regions in Europe, North America, and Asia before storing the data in Amazon S3. The application must comply with local data-protection and storage regulations. Data residency and processing must take place within the same continent. The application must also retain audit trails of its decision-making processes and provide data-classification capabilities. Which solution meets these requirements? | – | |
| 35 | A company is building a generative AI (GenAI)-powered customer support application that uses Amazon Bedrock foundation models (FMs). The application must retain conversational context across multiple interactions with the same user. It must run clarification workflows to address ambiguous user queries. The company must retain encrypted records of every user conversation for personalization. The application must support thousands of concurrent users while responding quickly to each user. Which solution meets these requirements? | – | |
| 36 | A financial services company is building a customer-service AI assistant using Amazon Bedrock. The AI assistant must not provide investment advice to users. It must block harmful content, mask personally identifiable information (PII), and retain audit trails for compliance reporting. The AI assistant must apply content filtering to both user inputs and model responses according to content sensitivity. The company needs an Amazon Bedrock guardrail configuration that effectively enforces these policies with minimal false positives. The solution must support multiple handling strategies for multiple sensitive-content types. Which solution meets these requirements? | – | |
| 37 | A media company must use Amazon Bedrock to establish a robust governance process for AI-generated content. The company must manage hundreds of prompt templates. Multiple teams use the templates in multiple AWS Regions to generate content. The solution must provide version control with approval workflows that include notifications for pending reviews. It must also provide detailed audit trails that record prompt activities and consistent prompt parameterization to enforce quality standards. Which solution will satisfy these requirements? | – | |
| 38 | A medical device company wants to provide an AI assistant with reports of medical procedures that used the company’s devices. To safeguard patient privacy, the AI assistant must reveal patient personally identifiable information (PII) only to surgeons. For engineers, the AI assistant must redact PII. The AI assistant must reference only medical reports that are less than 3 years old. The company stores reports in an Amazon S3 bucket immediately after each report is published. The company has already configured an Amazon Bedrock knowledge base. The AI assistant uses Amazon Cognito for user authentication. Which solution meets these requirements? | – | |
| 39 | Example Corp operates a personalized video-generation service used by millions of enterprise customers. Customers create marketing videos by submitting prompts to the company’s proprietary generative AI (GenAI) model. To improve output relevance and personalization, Example Corp wants to enrich prompts with customer-specific context, including product preferences, customer attributes, and business history. The customers have strict data-governance requirements. They must retain full ownership and control of their data. They do not need real-time access; however, semantic accuracy must be high and retrieval latency must stay low to support customer-experience use cases. Example Corp wants to minimize architectural complexity in its integration pattern. It does not want to deploy and manage services in each customer’s environment unless necessary. Which solution meets these requirements? | – | |
| 40 | An insurance company uses its existing Amazon SageMaker AI infrastructure to support a web-based application that lets customers predict their insurance premiums. The company keeps the customer data used to train the SageMaker AI model in an Amazon S3 bucket. The dataset is growing rapidly. The company needs a solution to continuously retrain the model. When an employee uploads a new customer-data file to the S3 bucket, the solution must automatically retrain and redeploy the model to the application. Which solution meets these requirements? | – | |
| 41 | A financial services company is rolling out a generative AI (GenAI) application that uses Amazon Bedrock to help customer service representatives deliver personalized investment advice to customers. The company must implement a comprehensive governance solution that follows responsible AI practices and satisfies regulatory requirements. The solution must detect and prevent hallucinations in recommendations. It must include safety controls for customer interactions, monitor model behavior drift in real time, and retain audit trails of all prompt-response pairs for regulatory review. The company must deploy the solution within 60 days. The solution must integrate with the company's existing compliance dashboard and respond to customers within 200 ms. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 42 | A company has deployed an AI assistant as a React application that uses AWS Amplify, an AWS AppSync GraphQL API, and Amazon Bedrock Knowledge Bases. The application uses the GraphQL API to invoke the Amazon Bedrock RetrieveAndGenerate API for knowledge base interactions. The company configures an AWS Lambda resolver with the RequestResponse invocation type. Application users report frequent timeouts and slow response times. Users report these issues more often for complex questions that require longer processing. The company needs a solution to resolve these performance issues and improve the user experience. Which solution will meet these requirements? | – | |
| 43 | A financial services company uses multiple foundation models (FMs) through Amazon Bedrock for its generative AI (GenAI) applications. To meet a new regulation governing GenAI use with sensitive financial data, the company requires a token-management solution. The token-management solution must proactively alert when applications near model-specific token limits. It must also handle more than 5,000 requests per minute and retain token-usage metrics to allocate costs among business units. Which solution will satisfy these requirements? | – | |
| 44 | A company operates a Retrieval Augmented Generation (RAG) application that uses Amazon Bedrock Knowledge Bases for regulatory compliance queries. The application uses the RetrieveAndGenerateStream API. It retrieves relevant documents from a knowledge base containing more than 50,000 regulatory documents, legal precedents, and policy updates. The RAG application is generating suboptimal responses because initial retrieval frequently returns documents that are semantically similar but contextually irrelevant. These poor responses are leading to model hallucinations and incorrect regulatory guidance. The company must improve RAG application performance so that it returns more relevant documents. Which solution meets this requirement with the LEAST operational overhead? | – | |
| 45 | A healthcare company uses Amazon Bedrock to build a real-time patient-care AI assistant that answers queries for separate departments responsible for clinical inquiries, insurance verification, appointment scheduling, and insurance claims. The company wants to use a multi-agent architecture. The company must ensure that the AI assistant is scalable and can onboard new patient features. The AI assistant must be capable of handling thousands of parallel patient interactions. The company must ensure that patients receive suitable domain-specific responses to their queries. Which solution will meet these requirements? | – | |
| 46 | A company is building a generative AI (GenAI) application that analyzes customer service calls in real time and produces suggested responses for human customer service agents. The application must handle 500,000 concurrent calls during peak hours, with less than 200 ms end-to-end latency for every suggestion. The company uses an existing architecture to transcribe customer-call audio streams. The application must stay within a predefined monthly compute budget and retain auto-scaling capabilities. Which solution meets these requirements? | – | |
| 47 | A finance company is building an AI assistant to help clients plan investments and manage their portfolios. The company identifies several high-risk conversation patterns, such as requests for specific stock recommendations or guaranteed returns. These high-risk conversation patterns could result in regulatory violations if the company cannot apply appropriate controls. The company must ensure that the AI assistant does not provide unsuitable financial advice, produce content about competitors, or make claims that are not factually supported by the company's approved financial guidance. The company wants to use Amazon Bedrock Guardrails to implement a solution. Which combination of steps will satisfy these requirements? | – | |
| 48 | A hotel company wants to improve a legacy Java-based property management system (PMS) by adding AI capabilities. The company plans to use Amazon Bedrock Knowledge Bases to give staff room-availability information and hotel-specific details. The solution must keep separate access controls for every hotel the company manages. It must deliver room-availability information in near real time and maintain consistent performance during peak-use periods. Which solution will satisfy these requirements? | – | |
| 49 | A bank is developing a generative AI (GenAI) application that uses Amazon Bedrock to evaluate loan applications from scanned financial documents. The application must extract structured data from the documents. It must redact personally identifiable information (PII) before inference. It must use foundation models (FMs) to generate approvals. It must route document-extraction results with low confidence to human reviewers located in the same AWS Region as the loan applicant. The company must ensure the application meets strict Regional data-residency and auditability requirements. The application must scale to process 25,000 applications per day and provide 99.9% availability. Which combination of solutions meets these requirements? | – | |
| 50 | A financial services company is developing a Retrieval Augmented Generation (RAG) application that uses Amazon Bedrock to produce summaries of market activities. The application depends on a vector database that stores a small proprietary dataset with a low index count. The application must run similarity searches, and the Amazon Bedrock model responses must maximize accuracy while maintaining high performance. The company needs to configure the vector database and integrate it with the application. Which solution meets these requirements? | – | |
| 51 | A company is building a customer-support application that uses Amazon Bedrock foundation models (FMs) to deliver real-time AI assistance to the company's employees. The application must show AI-generated responses character by character as they are produced. It must support thousands of concurrent users with minimal latency. Responses generally take 15 to 45 seconds to complete. Which solution meets these requirements? | – | |
| 52 | A medical company uses Amazon Bedrock to run a clinical-documentation summarization system. The system generates inconsistent summaries when it processes complex clinical documents, although it performed well with simple clinical documents. The company requires a solution that diagnoses the inconsistencies, compares prompt performance against established metrics, and preserves historical records of prompt versions. Which solution meets these requirements? | – | |
| 53 | A company has provisioned Amazon Q Developer Pro licenses for every developer. The company maintains a list of approved resources that developers must use when developing applications. The approved resources include internal libraries, proprietary algorithmic techniques, and sample code with approved styling. A new developer team is using Amazon Q Developer to build a new Java-based application. The company must ensure that the new team uses the company’s approved resources. The company does not want to make any project-level modifications. Which solution meets these requirements? | – | |
| 54 | A retail company is building a customer-service application that must handle 10,000 daily queries about products, orders, and warranties. The application must be able to answer queries about 50,000 product documents that are updated daily. The application must integrate with an order-management API to check order status and help process returns. The application must preserve context across multi-turn customer interactions. The company must collect complete audit trails for application responses. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 55 | A financial services company is developing a customer support application that retrieves relevant financial-regulation documents from a database according to semantic similarity with user queries. The application must integrate with Amazon Bedrock to generate responses. It must be able to search documents in English, Spanish, and Portuguese, and filter documents by metadata such as publication date, regulatory agency, and document type. The database holds approximately 10 million document embeddings. To reduce operational overhead, the company needs a solution that minimizes management and maintenance work. The application must deliver low-latency responses for real-time customer interactions. Which solution meets these requirements? | – | |
| 56 | A financial services company uses an AI application to process financial documents with Amazon Bedrock. During business hours, the application processes approximately 10,000 requests per hour and therefore requires consistent throughput. The company uses the CreateProvisionedModelThroughput API to buy provisioned throughput. Amazon CloudWatch metrics show that the provisioned capacity is unused while on-demand requests are being throttled. The company discovers the following code in the application: The company needs the application to use the provisioned throughput and resolve the throttling issues. Which solution will meet these requirements? | – | |
| 57 | A company configures a landing zone in AWS Control Tower. The company handles sensitive data that must stay within the European Union. The company must use only the eu-central-1 Region. The company uses SCPs to enforce data-residency policies. GenAI developers at the company are assigned IAM roles with full permissions for Amazon Bedrock. The company must ensure that GenAI developers can use the Amazon Nova Pro model through Amazon Bedrock only by using cross-Region inference (CRI) and only in eu-central-1 . The company enables model access for the GenAI developer IAM roles in Amazon Bedrock. However, when a GenAI developer tries to invoke the model through the Amazon Bedrock Chat/Text playground, the GenAI developer receives the following error. User: arn:aws:sts::123456789012:assumed-role/AssumedDevRole/DevUserName Action: bedrock:InvokeModelWithResponseStream On resource(s): arn:aws:bedrock:eu-west-3::foundation-model/amazon.nova-pro-v1:0 Context: a service control policy explicitly denies the action The company needs a solution that resolves the error. The solution must retain the company’s existing governance controls and provide precise access control. The solution must comply with the company’s existing data-residency policies. Which combination of solutions meets these requirements? | – | |
| 58 | A global company is developing an AI assistant that uses RAG. The company requires the AI assistant to deliver near-real-time, low-latency performance. The AI assistant must serve multiple geographic areas. The company’s customers will use proprietary data with the AI assistant, and that proprietary data must not leave the company’s immediate geographic area. Which solution will satisfy these requirements? | – | |
| 59 | A healthcare company uses Amazon Bedrock to develop a system that assists practitioners with clinical decision-making. The system must give physicians treatment recommendations based only on approved medical documentation and must cite the specific sources. The system must not hallucinate or generate factually incorrect information. Which solution will satisfy these requirements with the LEAST operational overhead? | – | |
| 60 | An ecommerce company uses Amazon Bedrock to build a customer-service AI assistant. The AI assistant must process more than 50,000 customer inquiries each day. During promotional events, the AI assistant occasionally has traffic spikes of up to 150,000 inquiries per day. Analysis indicates that 40% of inquiries follow similar patterns and share the same context. A GenAI developer must design a solution that ensures low latency and consistent performance for the AI assistant during traffic spikes. Which solution will meet these requirements in the MOST cost-effective way? | – | |
| 61 | A bank is building a generative AI (GenAI)-powered AI assistant that uses Amazon Bedrock to help the bank’s website users with account inquiries and financial guidance. The bank must ensure that the AI assistant does not disclose any personally identifiable information (PII) during customer interactions. The AI assistant must not transmit PII in prompts to the GenAI model. It must not respond to customer requests for investment advice. The bank must gather audit logs for all customer interactions, including any images or documents transmitted during those interactions. Which solution meets these requirements with the LEAST operational effort? | – | |
| 62 | A company is building an internal generative AI (GenAI) assistant with Amazon Bedrock to summarize corporate documents for several business units. The GenAI assistant must produce responses in a consistent format that includes a document summary, business-risk classification, and terms flagged for review. The GenAI assistant must tailor the response tone to each user’s business unit, such as legal, human resources, or finance. The GenAI assistant must block hate speech, inappropriate topics, and sensitive information such as personal health information. The company needs a solution for centrally managing prompt variants across business units and teams. The company wants to minimize ongoing orchestration work and maintenance of post-processing logic. The company also needs to be able to adjust the GenAI assistant’s content-moderation criteria over time. Which solution meets these requirements with the LEAST maintenance overhead? | – | |
| 63 | A wildlife conservation agency runs zoos around the world. It uses a variety of sensors, trackers, and audiovisual recorders to observe animal behavior. The agency wants to introduce a generative AI (GenAI) assistant that can ingest multimodal data to analyze animal behavior. The GenAI assistant must support natural-language queries, avoid speculative interpretations of behavior, and retain audit logs for ethical research audits. Which solution fulfills these requirements? | – | |
| 64 | A company uses AWS Lambda and REST APIs to build a reasoning agent that automates support workflows. The system must retain memory across interactions, share relevant agent state, and support both event-driven and synchronous invocation. It must also enforce access control and session-based permissions. Which combination of steps delivers the MOST scalable solution? | – | |
| 65 | A company offers a service that helps users worldwide discover new restaurants. The service has 50 million monthly active users. The company plans to implement a semantic search solution over a database containing 20 million restaurants and 200 million reviews. The company currently stores this data in a PostgresQL database. The solution must support complex natural-language queries and return results for at least 95% of queries within 500 ms. It must preserve data freshness for restaurant details that are updated hourly. The solution must also scale cost-effectively during periods of peak usage. Which solution meets these requirements with the LEAST development effort? | – | |
| 66 | A company uses Amazon Bedrock to build a customer-support AI assistant. The AI assistant must answer customer questions about their accounts. It must not disclose personal information in its responses. The company must comply with data-residency policies by ensuring all processing takes place in the same AWS Region in which each customer is located. Before making the AI assistant available to customers, the company wants to assess how effectively it prevents personal-information exposure. Which solution meets these requirements? | – | |
| 67 | A company uses Amazon Bedrock to implement a Retrieval Augmented Generation (RAG)-based system that provides medical information to users. The company must compare multiple chunking strategies, assess the generation quality of two foundation models (FMs), and enforce quality thresholds for deployment. Which Amazon Bedrock evaluation configuration meets these requirements? | – | |
| 68 | A financial services company must preprocess unstructured data, including customer transcripts, financial reports, and documentation. The company stores this unstructured data in Amazon S3 to support an Amazon Bedrock application. The company must validate data quality, produce auditable metadata, monitor data metrics, and customize text chunking to optimize foundation model (FM) performance. Which solution meets these requirements with the LEAST development effort? | – | |
| 69 | A financial technology company uses Amazon Bedrock to develop an assessment system for its customer-service AI assistant. The AI assistant must give financial recommendations that are factually correct, compliant with financial regulations, and appropriate in conversation. The company must combine automated quality assessments at scale with targeted human review of critical interactions. Which solution will satisfy these requirements? | – | |
| 70 | A GenAI developer is assessing Amazon Bedrock foundation models (FMs) to improve a Europe-based company’s internal business application. The company has a multi-account landing zone in AWS Control Tower. The company uses SCPs to permit its accounts to use only the eu-north-1 Region and the eu-west-1 Region. All customer data must stay in private networks within the approved AWS Regions. The GenAI developer chooses an FM after analysis and testing and hosts the model in the eu-central-1 Region and the eu-west-3 Region. The GenAI developer must enable the company’s employees to access the FM. The GenAI developer must ensure that FM requests are private and remain in the same Regions as the FM. Which solution meets these requirements? | – | |
| 71 | A company operates a generative AI (GenAI)-powered summarization application in an application AWS account that uses Amazon Bedrock. The application architecture contains an Amazon API Gateway REST API that routes requests to AWS Lambda functions attached to private VPC subnets. The application summarizes sensitive customer records that the company stores in a governed data lake in a centralized data storage account. The company has enabled Amazon S3, Amazon Athena, and AWS Glue in the data storage account. The company must ensure that the application's calls to Amazon Bedrock use only private connectivity between the company’s application VPC and Amazon Bedrock. The company’s data lake must offer fine-grained, column-level access across the company’s AWS accounts. Which solution meets these requirements? | – | |
| 72 | A financial services company is building a generative AI (GenAI) application for both premium and standard customers. The application uses AWS Lambda functions behind an Amazon API Gateway REST API to process requests. The company must dynamically switch between AI models according to each user's customer tier. The company also wants to conduct A/B testing for new features without redeploying code. The company must validate model parameters, such as temperature and maximum token limits, before applying changes. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 73 | A company runs multiple Amazon Bedrock-based generative AI (GenAI) applications across several business units for customer service, content generation, and document analysis. Some applications have unpredictable token-consumption patterns. The company needs a comprehensive observability solution that delivers real-time visibility into token-usage patterns across multiple models. The observability solution must support custom dashboards for multiple stakeholder groups and offer alerting for token consumption across all foundational models used by the company’s applications. Which combination of solutions will meet these requirements with the LEAST operational overhead? | – | |
| 74 | A software company uses Amazon Q Business to build an AI assistant that lets employees access company information and personal information through natural-language prompts. The company stores this information in an Amazon S3 bucket. Each department has a dedicated prefix in the S3 bucket. Every object name includes the S3 prefix for the department to which it belongs. Each department can belong to only one group in AWS IAM Identity Center. Each employee belongs to one department. The company configures Amazon Q Business to access data in an S3 bucket as a data source. The company must ensure that the AI assistant honors access controls according to the user's IAM Identity Center group membership. Which solution meets this requirement with the LEAST operational overhead? | – | |
| 75 | A company uses Amazon Bedrock and Anthropic Claude 3 Haiku to build an AI assistant. The AI assistant typically handles 10,000 requests per hour, but during peak-use periods it experiences surges of up to 30,000 requests per hour. The AI assistant must respond within 2 seconds while operating across multiple AWS Regions. The company finds that, during peak-use periods, the AI assistant has throughput bottlenecks that result in increased latency and occasional request timeouts. The company must address these performance issues. Which solution will meet this requirement? | – | |
| 76 | A company is developing a video-analysis platform on AWS. The platform will analyze a large video archive using Amazon Rekognition and Amazon Bedrock. It must comply with predefined privacy standards, use secure model I/O, control foundation model (FM) access patterns, and provide an audit trail showing who accessed what and when. Which solution meets these requirements? | – | |
| 77 | A company is building a generative AI (GenAI) application that uses Amazon Bedrock foundation models (FMs). The application includes several custom tool integrations. Despite steady user traffic, the application has encountered unexpected surges in token consumption. The company requires a solution that uses Amazon Bedrock model invocation logging to monitor InputTokenCount and OutputTokenCount metrics. The solution must detect unusual tool-usage patterns and determine which specific tool integrations are responsible for abnormal token consumption. It must also automatically adjust thresholds as traffic patterns evolve. Which solution meets these requirements? | – | |
| 78 | A healthcare company is building a document management system that stores medical research papers in an Amazon S3 bucket. The company must create a comprehensive metadata framework to improve search precision for a generative AI (GenAI) application that analyzes the research papers. The metadata framework must include document timestamps, author details, and research-domain classifications. The solution must preserve a consistent metadata structure for every uploaded document. The solution must enable foundation models (FMs) to understand document context without accessing the complete content. Which solution will meet these requirements? | – | |
| 79 | A company is developing a generative AI (GenAI) application that processes financial reports and provides summaries to analysts. The application must operate in two compute environments. In one environment, an AWS Lambda function must use the Python SDK to analyze reports on demand. In the other environment, Amazon EKS containers must use the JavaScript SDK to batch-process multiple reports on a schedule. The application must maintain conversational context during multi-turn interactions, use the same foundation model (FM) in both environments, and provide consistent authentication. Which solution meets these requirements? | – | |
| 80 | A company is building a customer communication platform that uses an AI assistant powered by an Amazon Bedrock foundation model (FM). The AI assistant summarizes customer messages and creates initial response drafts. The company plans to use Amazon Comprehend to implement layered content filtering. The layered filtering must prevent the sharing of offensive content, protect customer privacy, and identify potential solicitation of inappropriate advice. Inappropriate advice solicitation includes requests for unethical practices, harmful activities, or manipulative behaviors. The solution must preserve acceptable overall response times; therefore, all pre-processing filters must complete before content reaches the FM. Which solution meets these requirements? | – | |
| 81 | A retail company operates a generative AI (GenAI) product-recommendation application that uses Amazon Bedrock. The application recommends products to customers according to browsing history and demographics. The company must implement fairness evaluation across multiple demographic groups to identify and quantify bias in recommendations between two prompt approaches. The company wants to gather and monitor fairness metrics in real time. The company must receive an alert when the fairness metrics reveal a discrepancy greater than 15% between demographic groups. The company must receive weekly reports that compare the performance of the two prompt approaches. Which solution meets these requirements with the LEAST custom development effort? | – | |
| 82 | A company is deploying a serverless inference API with AWS Lambda. The API will dynamically invoke multiple AI models hosted on Amazon Bedrock. The company must design a solution that can switch model providers in real time without changing or redeploying Lambda code. The design must provide safe configuration rollouts, validation, and rollback capabilities. Which solution meets these requirements? | – | |
| 83 | A company plans to deploy multiple generative AI (GenAI) applications to five independent business units operating across multiple countries in Europe and the Americas. Each application uses Amazon Bedrock Retrieval Augmented Generation (RAG) patterns with knowledge bases specific to each business unit that store terabytes of unstructured data. The company must create well-architected, standardized components for security controls, observability practices, and deployment patterns across all GenAI applications. The components must be reusable, versioned, and governed consistently. Which solution meets these requirements? | – | |
| 84 | An elevator service company has developed an AI assistant application using Amazon Bedrock. The application produces elevator maintenance recommendations to support the company’s elevator technicians. The company uses Amazon Kinesis Data Streams to collect elevator sensor data. New regulatory rules require a human technician to review every AI-generated recommendation. The company needs to establish human-oversight workflows to review and approve AI recommendations. The company must retain all human technician review decisions for audit purposes. Which solution meets these requirements? | – | |
| 85 | A healthcare organization uses Amazon Bedrock to create a Retrieval Augmented Generation (RAG) application that assists practitioners with clinical decision-making. The application must provide high accuracy when retrieving patient information, detect hallucinations in generated content, and lower human-review costs. Which solution meets these requirements? | – | |
| 86 | A software as a service (SaaS) company is developing a recommendation model that uses Amazon SageMaker AI to support an application that recommends airline cabin upgrades to customers. The company will host SageMaker AI models on Amazon Bedrock by using Amazon Bedrock Custom Model Import. Airline companies will use the application to send customized offers to customers. The model must analyze customers' travel history to make more relevant recommendations. The company stores customer travel history data in an Amazon RDS database. The company must ensure that the application provides consistent, relevant, and accurate results across multiple airlines and customer populations. Which solution meets these requirements? | – | |
| 87 | A financial-services company is building a customer-service AI assistant application that uses a foundation model (FM) in Amazon Bedrock. The application must provide transparent responses by documenting its reasoning and citing the sources used for Retrieval Augmented Generation (RAG). It must capture comprehensive audit trails for every user response. The application must support up to 10,000 concurrent users and respond to each customer inquiry within 2 seconds. Which solution meets these requirements with the least operational overhead ? | – | |
| 88 | A company uses an AI assistant application to summarize its website content and provide information to customers. The company plans to use Amazon Bedrock to provide the application with access to a foundation model (FM). The company must deploy the AI assistant application to both a development environment and a production environment. The solution must integrate the environments with the FM. The company wants to evaluate the effectiveness of different FMs in each environment. The solution must allow product owners to easily switch between FMs for testing in each environment. Which solution meets these requirements? | – | |
| 89 | A company uses Amazon Bedrock to create a customer-facing AI assistant that handles sensitive customer inquiries. The company must use defense-in-depth safety controls to block sophisticated prompt-injection attacks, retain audit logs for every safety intervention, and provide cross-Region failover for the AI assistant. Which solution meets these requirements? | – | |
| 90 | A financial services company is building a real-time generative AI (GenAI) assistant to assist human call center agents. The GenAI assistant must transcribe live customer speech, analyze context, and deliver incremental suggestions to call center agents while the customer is still speaking. To maintain responsiveness, the GenAI assistant must keep end-to-end latency below 1 second from speech to the initial response display. The architecture must use only managed AWS services and support bidirectional streaming so that call center agents receive real-time updates. Which solution meets these requirements? | – | |
| 91 | A company uses AWS Lake Formation to configure a data lake that contains databases and tables for multiple business units across multiple AWS Regions. The company wants to use a foundation model (FM) through Amazon Bedrock for fraud detection. The FM must ingest sensitive financial data from the data lake. The data includes some customer personally identifiable information (PII). The company must design an access-control solution that prevents PII from appearing in a production environment. The FM must access only authorized data subsets with PII redacted from specific data columns. The company must capture audit trails for all data access. Which solution meets these requirements? | – | |
| 92 | A company uses Amazon Bedrock to build a Retrieval Augmented Generation (RAG) system. The RAG system uses an Amazon Bedrock knowledge base that relies on an Amazon S3 bucket as its data source for emergency-news video content. The system retrieves transcripts, archived reports, and related documents from the S3 bucket. The RAG system uses state-of-the-art embedding models and a high-performing retrieval configuration. However, users report slow responses and irrelevant results, resulting in lower user satisfaction. The company observes that vector searches evaluate too many documents across too many content types and over excessively long time periods. The company determines that the underlying models would not benefit from additional fine-tuning. The company must improve retrieval accuracy by applying smarter constraints. The company wants a solution that requires minimal changes to the existing architecture. Which solution meets these requirements? | – | |
| 93 | An ecommerce company uses Amazon Bedrock to develop a generative AI (GenAI) application. The application uses AWS Step Functions to orchestrate a multi-agent workflow that produces detailed product descriptions. The workflow contains three sequential states: a description generator, a technical-specifications validator, and a brand-voice consistency checker. Each state generates intermediate reasoning traces and outputs that are passed to the following state. The application uses an Amazon S3 bucket for process storage and output storage. During testing, the company finds that outputs passed between Step Functions states frequently exceed the 256 KB quota, causing workflow failures. A GenAI Developer must revise the application architecture to efficiently handle the Step Functions 256 KB quota while maintaining workflow observability. The revised architecture must retain the existing multi-agent reasoning and acting (ReAct) pattern. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 94 | A legal research company operates a Retrieval Augmented Generation (RAG) application that uses Amazon Bedrock and Amazon OpenSearch Service. The application stores 768-dimensional vector embeddings for 15 million legal documents, including statutes, court rulings, and case summaries. The company’s current chunking strategy divides text into fixed-length blocks of 500 tokens. This strategy frequently separates contextually connected information, such as legal arguments, court opinions, or statute references, into different chunks. Researchers report that generated outputs often leave out critical context or reference outdated legal information. Recent application logs show a 40% rise in response times. The p95 latency metric is greater than 2 seconds. The company anticipates that the application’s storage requirements will increase from 90 GB to 360 GB within one year. The company needs a solution that improves retrieval relevance and system performance at scale. Which solution meets these requirements? | – | |
| 95 | A healthcare company is building an application to process medical queries. The application must answer complex queries with high accuracy while reducing semantic dilution. It must reference domain-specific terminology in medical documents to reduce ambiguity in medical terms. The application must also respond to 1,000 queries per minute with response times of less than 2 seconds. Which solution meets these requirements with the LEAST operational overhead? | – | |
| 96 | A company uses Amazon Bedrock to build an application that helps researchers apply for grants. The application is based on an Amazon Nova Pro foundation model (FM). It has four required inputs and must return responses in a consistent text format. The company wants to receive a notification in Amazon Bedrock when a response contains bullying language, but does not want every flagged response to be blocked. The company creates an Amazon Bedrock flow that accepts an input prompt and sends it to the Amazon Nova Pro FM. The Amazon Nova Pro FM returns a response. Which additional steps must the company take to meet these requirements? | – | |
| 97 | A company operates a generative AI (GenAI) application that uses Amazon Bedrock to deliver real-time responses to customer queries. The company has observed intermittent API-call failures to foundation models (FMs) during periods of peak traffic. The company requires a solution that handles transient errors and delivers detailed observability into FM performance. The solution must prevent cascading failures during throttling events and provide distributed tracing across service boundaries to identify contributors to latency. The solution must also support correlating performance issues with specific FM characteristics. Which solution satisfies these requirements? | – | |
| 98 | A financial services company is developing a generative AI application that lets business analysts query sensitive customer data using natural language. A GenAI developer needs to implement a content safety framework that performs text-to-SQL transformations while preventing harmful outputs. The solution must: Which solution will meet these requirements? | – | |
| 99 | A company wants to build a system that automatically generates study materials from multiple content sources. The content sources include: The system must meet the following requirements: Which solution will meet these requirements? | – | |
| 100 | A healthcare company wants to build a proof-of-concept application that uses Amazon Bedrock to automatically summarize medical documents. The company has 3 weeks to validate the accuracy of the application. The solution must: Which solution will meet these requirements? | – | |
| 101 | A company wants to select a new foundation model (FM) for its AI assistant. A GenAI developer needs to generate evaluation reports to help a data scientist assess the quality and safety of various foundation models (FMs). The data scientist provides the GenAI developer with sample prompts for evaluation. The GenAI developer wants to use Amazon Bedrock to automate report generation and evaluation. Which solution will meet this requirement? | – | |
| 102 | A media company is building an AI-powered content moderation system using Amazon Bedrock. The system first classifies text using a small, low-latency model, then escalates requests whose confidence score is below 0.65 to a larger, more expensive model. The solution must meet the following requirements: process requests asynchronously so that a slow large-model escalation never blocks new submissions; scale automatically to absorb sudden traffic spikes; minimize cost by invoking the larger model only for the requests that actually need it; and remain resilient so that an in-flight request is not lost if a processing component fails. Which solution will meet these requirements? | – | |
| 103 | A social messaging company is building an AI chat assistant using Amazon Bedrock. The company must ensure that every inference complies with an approved safety policy. Specifically, the company wants to: filter both the incoming prompt and the generated response against the same approved guardrail so unsafe content never reaches an end user; apply guardrail filtering to streamed responses in real time rather than only after generation completes; route flagged content to a queue for human review; and technically guarantee that no inference call can bypass the approved guardrail, rather than relying on developer discipline alone. Which solution will meet these requirements? | – | |
| 104 | A company built a multimodal content-analysis application on Amazon Bedrock. The application routes different content types (text, images, and code) to specialized foundation models (FMs). The application must handle multiple types of routing decisions: simple, low-latency routing that can be resolved from file extension alone without added orchestration overhead; complex routing decisions that require semantic analysis of the content itself; an auditable record of how each routing decision was made; and automatic fallback to an alternate FM if the originally selected model fails or is unavailable. Which solution will meet these requirements? | – | |
| 105 | A company is building a multicloud generative AI (GenAI)-powered secret resolution application that uses Amazon Bedrock and Agent Squad. The application resolves secrets from multiple sources, including key stores and hardware security modules (HSMs), using AWS Lambda functions to retrieve the secrets. The application has the following characteristics: several Agent Squad agents run in sequence to resolve each secret request, and retrieved secrets carry short-lived TTLs before they expire; prompt flow templates that guide agent behavior are updated periodically as new secret sources are added. During testing, the company identifies the following issues: because the agents run sequentially, some secrets expire before the workflow finishes resolving them; downstream agents sometimes act on stale secret metadata instead of the most recently retrieved values; and a recent faulty prompt template update caused a wave of agent errors with no quick way to roll back to the previous known-good template. The company must resolve these performance issues. Which solution will meet this requirement? | – | |
| 106 | A university is developing an AI-powered application composed of several sub-applications, including AI assistants, assignment graders, and internal analytics tools. The university is defining and testing multiple prompts across various foundation models (FMs) and wants to: version prompts so a tested prompt can be reused consistently across the assistant, grader, and analytics sub-applications; parameterize prompts with variables so each sub-application can supply its own inputs; maintain an audit trail of prompt changes over time; and compose prompts with FMs and other AWS services into repeatable workflows. Which combination of solutions will meet these requirements with the LEAST operational overhead? | – | |
| 107 | A financial services company is building a natural language processing (NLP) application that uses an AWS Lambda function to process customer trade inquiries using Amazon Bedrock foundation models (FMs). The Lambda function needs to generate comprehensive trade analysis responses that typically: take 15–20 seconds to fully generate given the depth of analysis required, and produce long, detailed responses covering multiple aspects of a trade. The application must also: give customers a perceived response within 10 seconds even though full generation takes longer, and retain complete response records for 10 years to meet financial services regulatory requirements. Which solution will meet these requirements? | – | |
| 108 | A financial services company handles over 10,000 customer inquiries each day using a multi-agent GenAI application built on Amazon Bedrock AgentCore. The agents in this application invoke several custom tools. During peak usage periods, users report that these custom tools experience failure rates as high as 40%, and the tools perform inconsistently across different teams within the company. A GenAI developer needs to implement an observability solution that delivers end-to-end visibility into agent interactions and tool behavior. The solution must: provide end-to-end tracing across agent and tool invocations without the team having to build and maintain custom instrumentation; surface error, throttling, and latency metrics during peak usage so failing tools can be pinpointed quickly; and support comparing tool performance across the different teams that use them. Which solution meets these requirements? | – | |
| 109 | A company is building a customer support chat assistant that relies on an Amazon Bedrock foundation model (FM). The company plans to upgrade to a newer FM version but needs a validation system that can detect semantic drift in the assistant's responses, so that performance and functionality remain consistent for end users. The company needs a solution that can: compare responses from the new and existing FM versions using an existing set of 500 test prompts; quantify how much the new model's responses differ in meaning from the existing model's responses; and store results for historical comparison across future upgrades. Which solution will meet these requirements with the LEAST operational complexity? | – | |
| 110 | An ecommerce company uses an Anthropic Claude Sonnet model in Amazon Bedrock to generate product recommendations. An AWS Lambda function retrieves: the customer's complete purchase history, browsing activity, and stated preferences from a database. The function then sends this data directly to the Amazon Bedrock model through API calls. Recently, customers with extensive purchase histories have started receiving incomplete recommendations. Amazon CloudWatch logs for the Lambda function show execution timeouts, and CloudWatch logs for the Amazon Bedrock API calls show intermittent errors. Upon reviewing the logs, the company finds that some requests fail with context length exceeded errors, while other requests complete but appear to ignore portions of the input data. The company wants the recommendation system to take into account all customer data when generating recommendations, and it wants to use Amazon Bedrock Knowledge Bases to improve how the data is organized and retrieved. Which combination of solutions will meet these requirements? | – | |
| 111 | A company operates a customer service application that leverages Amazon Bedrock to generate personalized responses to customer inquiries. The company wants to set up a quality assurance process to evaluate how effective its prompts are and how well its model configurations perform across updates. This process needs to: automatically compare outputs from different prompt and model configurations against a custom set of test prompts; trigger a new evaluation automatically whenever a prompt template changes; and only allow a configuration to be promoted to production when its quality score exceeds a defined threshold. Which solution will meet these requirements? | – | |
| 112 | A retail company operates an application that provides product recommendations to customers on its website. The application uses Amazon Bedrock to generate these recommendations by dynamically building prompts and sending them to foundation models (FMs). A GenAI developer deploys an update to the application that instructs the FM to include a specific promotional message whenever it generates a response to prompts. During testing, the developer finds that: the FM omits the promotional message entirely in some responses despite the prompt instructing it to include one, and in other responses includes the message in a way that reads awkwardly alongside the recommendation. The GenAI developer needs to guarantee that the promotional message always appears in the FM's responses. Which solution meets this requirement? | – | |
| 113 | A company is building a generative AI (GenAI) application that uses Amazon Bedrock foundation models (FMs). The solution must meet the following requirements: authenticate users against the company's existing Microsoft Entra ID identity provider; restrict each department to only the specific Bedrock foundation model families it is approved to use; keep all traffic to Amazon Bedrock off the public internet; and maintain a complete audit trail of both the API calls made to Bedrock and the details of each model invocation. Which solution will meet these requirements? | – | |
| 114 | A healthcare company is building an AI application that retrieves medical literature to support doctors' research. The company plans to deploy this application across multiple countries. The application must index 50,000 text-heavy medical documents containing specialized terminology in English, French, and German, and it must deliver high search accuracy for that medical terminology. The company wants a solution requiring minimal custom code development and minimal ongoing maintenance. Which solution will meet these requirements? | – | |
| 115 | A publishing company is building a chat assistant powered by a containerized large language model (LLM) that runs on Amazon SageMaker AI. The architecture includes an Amazon API Gateway REST API that forwards user requests to an AWS Lambda function, which in turn invokes a SageMaker AI real-time endpoint hosting the LLM. Users are experiencing inconsistent response times. Analytics reveal that many chats are abandoned after users wait 2 seconds for the first token to appear. The company needs a solution that keeps p95 latency under 800 ms for interactive requests to the chat assistant. Which combination of solutions will meet this requirement? | – | |
| 116 | A company operates a generative AI application that uses multiple foundation models (FMs) from Amazon Bedrock to generate text. The application serves users across three AWS Regions and runs on AWS Lambda functions. The company needs to implement dynamic model selection based on response quality and latency metrics. The company must be able to switch between models without modifying or redeploying the application code. The company wants to gradually roll out new models, starting with 20% of traffic. The company also needs a solution that will automatically roll back if error rates exceed 1%. Which solution will meet these requirements? | – | |
| 117 | A financial services company is building an AI-powered search assistant to help investment advisors quickly retrieve investment data. The application runs as an AWS Lambda function and uses Amazon Bedrock, specifically an Amazon Bedrock knowledge base backed by Amazon OpenSearch Serverless as its data source. The application agent must manage collections at scale by automatically assigning access permissions to collections and indexes that match a specific pattern. While testing the knowledge base with Amazon Bedrock tools, the knowledge base sync process completes successfully. However, testing reveals: agent invocations that query the knowledge base intermittently fail with 403 permission-denied errors even though the underlying data was synced successfully, and newly created OpenSearch Serverless collections and indexes that match the intended naming pattern are not automatically receiving the access permissions the application expects. The company needs to resolve these permissions issues. Which combination of solutions will meet this requirement? | – | |
| 118 | A hospital is developing an AI application to assist medical clinicians with treatment decisions. The application uses Amazon Bedrock to analyze patient case histories and recommend diagnoses. The application must sustain sub-500 ms response times to integrate with the hospital's existing real-time clinical workflow. To comply with privacy regulations, the application must log every personally identifiable information (PII) handling decision for audits. The application must identify and remove PII from responses with at least 99% accuracy. Following the initial deployment, clinicians report that diagnostic summaries from the application sometimes contain patient names and medical record numbers that were not in the original case-history inputs. An investigation shows that Amazon Comprehend Medical successfully identifies and removes PII from inputs with 95% accuracy, and the application substitutes tokens for every detected entity before sending inputs to Amazon Bedrock. However, the application still generates patient-identifying information in approximately 3–5% of outputs. The company needs a solution that prevents the application from displaying PII in outputs while satisfying all other operational requirements. Which solution meets these requirements? | – | |
| 119 | A financial company is developing an AI-powered recommendation system. The system uses real-time market data and verified internal documents. It must provide evaluation capabilities that collect explicit user ratings and identify problematic responses in real time. It must also provide evaluation capabilities that monitor model performance over time and enable A/B testing of different prompt or model variants. The system must orchestrate multi-step workflows. These workflows must retrieve trusted knowledge, validate inputs, and generate recommendations. The system must securely retain all user feedback, flagged events, and audit logs in a compliance-ready immutable repository. The repository must provide write-once, tamper-evident storage appropriate for regulated audit retention. Which architecture meets these requirements? | – | |
| 120 | A financial services company uses Amazon Bedrock to analyze customer data stored in an Amazon S3 bucket. The data contains personally identifiable information (PII). The company needs to mask PII in foundation model (FM) responses. Which solution meets this requirement with the LEAST operational effort? | – | |
| 121 | A healthcare company is building an application that processes sensitive patient data and generates treatment summaries by using a foundation model (FM). The application must retain an audit trail for all prompts and completions. It must securely handle protected health information (PHI) throughout the processing lifecycle. The company must track every prompt-completion pair with the original patient data, while redacting any PHI from stored records. The company must also enforce healthcare-specific data-retention policies. Which solution meets these requirements? | – | |
| 122 | A company deploys a GenAI application that uses an Amazon Bedrock foundation model (FM) with custom prompts. The company must implement an automated quality-assurance system to validate FM outputs against expected responses and identify regressions over time. The solution must compare outputs with more than 500 golden examples by using semantic-similarity scoring. The solution must support regularly scheduled test rules. It must be able to scale to more than 2,000 test cases within 6 months without requiring architecture changes. The company wants to produce visualizations for quality metrics. The company must receive alerts when the solution detects quality degradation. Which solution meets these requirements? | – | |
| 123 | A healthcare company is deploying a clinical knowledge-base application on Amazon Bedrock that supplies medical information to doctors. During testing, the quality team finds that the generative AI (GenAI) model sometimes invents medical treatment recommendations that are not derived from the approved clinical guidelines. Before the application is released, the quality team must implement a solution to detect these hallucinations. The solution must compare model responses with verified medical information and identify semantic inconsistencies when users phrase similar questions differently. Which solution meets these requirements? | – | |
| 124 | A financial-services company must create a zero-touch promotion workflow for a multilingual AI assistant that automatically promotes prompt updates from a development environment to a production environment. The workflow must promote prompt updates only when the updates satisfy several criteria. The updates must increase accuracy in all five languages supported by the AI assistant. The updates must exhibit lower variance across similar queries than prior prompt versions. The updates must pass every regulatory-compliance check for content concerning investment risks and fee disclosures. The workflow must operate within the company's existing CI/CD pipeline, support comparisons between prompt versions, produce auditable evaluation reports, and remain cost-effective over time. Which solution meets these requirements? | – |