AIP-C01 AWS Certified Generative AI Developer - Professional Questions and Answers

Option C directly addresses both retrieval relevance and performance scalability. Fixed token chunking breaks semantic continuity in legal texts, causing incomplete context retrieval and degraded response quality. By switching to semantic chunking—based on legal arguments, clauses, or sections—the application preserves contextual integrity, improving retrieval accuracy and reducing hallucinations.

Regenerating embeddings aligned with the new chunk structure also improves vector search efficiency, reducing unnecessary comparisons and helping control latency as the dataset scales.

Option A increases cost and latency without fixing the core issue. Option B removes dynamic reasoning, which defeats the purpose of a legal RAG system. Option D discards vector semantics entirely and is unsuitable for nuanced legal research. Therefore, Option C is the correct and scalable solution.

Option C best satisfies the requirements because it combines application-aware observability, metric baselining, anomaly detection, and correlated alerting using fully managed AWS services with minimal operational overhead. Amazon CloudWatch Application Insights is designed to automatically monitor application health by analyzing metrics, logs, and events across EC2-based workloads. This aligns directly with the need to detect intermittent performance issues and deviations from expected behavior.

By publishing custom metrics using the CloudWatch embedded metric format, the application can track generative AI–specific signals such as recommendation quality indicators, token usage, request volume, and response latency from Amazon Bedrock foundation model calls. Adding dimensions such as request type or user segment enables fine-grained visibility into which workloads or customer groups are impacted when recommendation quality degrades.

A critical requirement is detecting degradation compared to established baselines and generating alerts within 10 minutes. CloudWatch anomaly detection automatically builds statistical models of normal behavior for time-series metrics and flags deviations without requiring manually tuned thresholds. This capability is well suited for monitoring foundation model behavior, which can vary subtly over time. When anomalies are detected, CloudWatch alarms can trigger notifications with contextual metric data quickly, meeting the alerting requirement.

CloudWatch Logs Insights complements the metric-based view by enabling log pattern analysis and correlation. Engineers can query application logs and model response logs to identify recurring error patterns or shifts in output behavior that explain why recommendations no longer align with user preferences. Application Insights further correlates metrics and logs to surface probable root causes, reducing mean time to resolution.

The other options lack one or more critical elements. Option A focuses on infrastructure-level metrics without baseline anomaly detection. Option B emphasizes tracing and auditing but does not provide automated performance deviation analysis. Option D offers flexibility but requires significantly more development and operational effort than a native CloudWatch-based solution.

Option B is the correct solution because it aligns with AWS guidance for building high-throughput, ultra-low-latency GenAI applications while maintaining predictable costs and automatic scaling. Amazon Bedrock provides access to foundation models that are specifically optimized for real-time inference use cases, including conversational and recommendation-style workloads that require responses within milliseconds.

Low-latency models in Amazon Bedrock are designed to handle very high request rates with minimal per-request overhead. Purchasing provisioned throughput ensures that sufficient model capacity is reserved to handle peak loads, eliminating cold starts and reducing request queuing during traffic surges. This is critical when supporting up to 500,000 concurrent calls with strict latency requirements.

Automatic scaling policies allow the application to dynamically adjust capacity based on demand, ensuring cost efficiency during off-peak hours while maintaining performance during peak usage. This directly supports the requirement to stay within a predefined monthly compute budget.

Option A fails because batch processing and complex reasoning models introduce higher latency and are not suitable for real-time suggestions. Option C introduces significantly higher operational and cost overhead due to dedicated GPU instances and manual scaling responsibilities. Option D is optimized for batch workloads and cannot meet the sub-200 ms latency requirement.

Therefore, Option B provides the best balance of performance, scalability, cost control, and operational simplicity using AWS-native GenAI services.

Option B is correct because the application is currently invoking the base foundation model identifier, which routes traffic to the on-demand capacity pool rather than the company’s purchased provisioned throughput. In Amazon Bedrock, provisioned throughput is attached to a specific provisioned resource created through the provisioned throughput APIs. To consume that reserved capacity, inference requests must target the provisioned resource identifier that represents the purchased throughput, not the generic model identifier used for on-demand inference.

The code snippet uses modelId="anthropic.claude-v2". This value selects the on-demand endpoint for that model. As a result, requests are subject to on-demand quotas and throttling behavior, while the provisioned throughput remains idle. This directly explains the CloudWatch observation: provisioned capacity metrics show unused capacity because no traffic is being directed to the provisioned resource, and the on-demand path is throttling because it is exceeding the applicable on-demand limits during peak volume.

Replacing the modelId value with the provisioned throughput ARN returned by the CreateProvisionedModelThroughput workflow ensures the runtime invocation is routed to the reserved capacity. Once traffic is directed correctly, the purchased model units provide the consistent throughput required for predictable performance during business hours, which is exactly why provisioned throughput is used.

Option A could increase capacity, but it does not fix the core issue that the application is not using the provisioned resource at all. Option C can reduce the impact of throttling temporarily, but it adds latency and does not guarantee consistent throughput; it also still wastes the provisioned capacity. Option D changes the response delivery mechanism, but throttling is a capacity routing and quota issue, not a streaming API issue.

Option B is the best fit because hierarchical chunking is designed to preserve local detail while keeping broader document context available during retrieval, which directly addresses the problem of questions spanning methodology, results, and discussion. In large scientific papers, a single answer often depends on linked paragraphs across adjacent sections. If the knowledge base retrieves only small, isolated chunks, the RAG system can cite text that is semantically close to a query term but not contextually correct, producing inconsistent answers and irrelevant citations.

With hierarchical chunking, the knowledge base creates child chunks that are small enough for high-precision vector similarity matching, such as 200 tokens, which improves the likelihood that the retrieved text is tightly related to the user’s query. At the same time, each child chunk is associated with a larger parent chunk, such as 1,000 tokens, which retains the surrounding narrative and section-level context. This structure helps the retrieval pipeline return passages that include the relevant subsection plus the explanatory framing that prevents misinterpretation, which is especially important in scientific writing where methods, results, and discussion are interdependent.

The configured overlap further reduces boundary effects where key statements split across chunks. This improves continuity for paragraphs that bridge sections, such as a results paragraph that references the methodological setup or a discussion paragraph interpreting a specific metric.

Option A can improve consistency slightly, but fixed-size chunking still risks separating related paragraphs and does not provide a built-in mechanism to retrieve broader context linked to precise matches. Option C can create more meaningful boundaries, but it does not guarantee the parent-level context that hierarchical chunking provides at retrieval time. Option D increases operational burden and is not practical at the scale of 25 million

Option B is the correct solution because Amazon Bedrock provisioned throughput is only used when the application explicitly invokes the provisioned model ARN, not the base foundation model ID. In the provided code, the application is calling the standard model identifier (anthropic.claude-v2), which routes requests to on-demand capacity instead of the purchased provisioned throughput.

When the CreateProvisionedModelThroughput API is used, Amazon Bedrock returns a provisioned model ARN that represents the reserved capacity. Applications must reference this ARN in the modelId parameter when invoking the model. If the base model ID is used instead, Bedrock treats the request as on-demand traffic, which explains why CloudWatch metrics show unused provisioned capacity alongside throttled on-demand requests.

Option A would increase capacity but would not fix the root cause because the application is not using the provisioned resource at all. Option C adds resiliency but does not ensure usage of provisioned throughput and would still incur throttling. Option D changes the response delivery mechanism but does not affect capacity routing.

Therefore, Option B directly resolves the throttling issue by correctly routing traffic to the reserved capacity and ensures that the company benefits from the provisioned throughput it has purchased.

Option C best satisfies the requirement to change routing decisions without redeploying code while supporting complex, frequently changing business logic at scale. AWS AppConfig is designed for centrally managing dynamic configuration (feature flags, rules, thresholds, and policy parameters) and deploying changes safely. It supports controlled deployments, validation, and rapid propagation of updated configuration values, which aligns with “real-time cost metrics that change hourly” and the need for “immediate propagation across thousands of concurrent requests.”

In this design, the Lambda function becomes the policy decision point. For each request, it evaluates user attributes (tier, transaction value), context (regulatory zone, Region), and live cost/performance thresholds stored in AppConfig to determine which Amazon Bedrock FM to invoke. Because the routing rules and FM identifiers are delivered as configuration, the company can switch models, adjust A/B testing weights, or update compliance routing rules by deploying new AppConfig configuration versions rather than pushing new application code. This reduces operational risk and accelerates iteration.

Exposing a single API Gateway endpoint also minimizes client complexity and keeps routing logic server-side, which is important when rules change frequently. Lambda can cache configuration between invocations (within the execution environment) to reduce repeated fetch overhead while still picking up changes quickly, enabling both low latency and rapid rule rollout under high concurrency.

Option A relies on Lambda environment variables, which are not intended for frequent real-time updates and typically require function configuration updates that are slower and operationally brittle. Option B uses mapping templates and stage variables, which are limited for complex rule evaluation and safe rollout patterns. Option D misuses authorizers for business routing, adds extra latency and complexity, and complicates observability and error handling by splitting decisioning from execution.

Option A is the correct solution because it uses native Amazon Bedrock governance and evaluation capabilities to meet regulatory, performance, and deployment timeline requirements with the least operational overhead.

Amazon Bedrock guardrails provide built-in safety controls that enforce responsible AI policies directly during inference. Custom content filters and toxicity detection protect customer interactions and prevent disallowed investment guidance patterns without requiring custom application logic. Guardrails operate inline and are optimized for low latency, which helps meet the strict 200 ms response-time requirement.

Hallucination detection is addressed through Amazon Bedrock Model Evaluation, which supports automated evaluation at scale using LLM-as-a-judge techniques. This enables the company to detect factual inaccuracies and policy violations systematically, without building custom evaluation pipelines or requiring extensive human review. Evaluation outputs can be surfaced as metrics.

Storing all prompt-response pairs in Amazon DynamoDB provides a low-latency, highly scalable audit store that aligns with financial regulatory requirements. Using TTL enforces data retention policies automatically, reducing compliance risk and storage overhead.

Amazon CloudWatch custom metrics integrate seamlessly with existing compliance dashboards, allowing near–real-time monitoring of safety interventions, hallucination rates, and drift indicators. CloudWatch anomaly detection can be applied to these metrics to surface behavior changes quickly.

Option B relies on custom Lambda logic and S3-based auditing, increasing latency and operational complexity. Option C introduces additional services that increase setup time and may exceed the 60-day deployment window. Option D uses non–Bedrock-native monitoring and adds unnecessary infrastructure layers.

Therefore, Option A provides the most complete, compliant, and low-overhead governance solution for a regulated GenAI financial services application.

Option B is the most appropriate solution because it directly uses Amazon Bedrock cross-Region inference profiles, which are designed to provide resilience and load distribution while respecting data residency boundaries. Cross-Region inference profiles allow applications to distribute inference requests across multiple Regions within a defined geographic boundary, such as Europe or North America, without requiring custom failover logic.

By specifying geographical codes in the inference profile ID, the application ensures that European user data is processed only within Europe-based Regions, satisfying regulatory requirements. At the same time, Bedrock automatically routes requests to healthy Regions within that geography when traffic spikes or service quotas are reached, improving availability and maintaining low latency.

Using separate Amazon API Gateway HTTP APIs for Europe and North America provides a clean, simple routing layer that directs users to the appropriate regional inference profile. This avoids complex custom routing or retry logic in application code and minimizes operational overhead.

Option A relies on custom routing and manual monitoring, which increases complexity and does not provide automatic resilience. Option C introduces custom retry and fallback logic that risks violating data residency requirements if misconfigured. Option D requires significant application-level failover logic and adds operational burden with Global Accelerator configuration.

Therefore, Option B best meets the requirements for low latency, data residency compliance, resilience during traffic spikes, and minimal operational complexity.

Option B is the correct solution because Amazon Bedrock evaluation jobs are purpose-built to assess prompt effectiveness, model behavior, and response quality in a repeatable and automated manner. Evaluation jobs support both quantitative metrics and LLM-based judgment, making them suitable for detecting subtle response quality regressions that simple sentiment or latency metrics cannot capture.

By using custom prompt datasets, the company can consistently test multiple prompt templates and model configurations against the same inputs. This enables accurate comparison across updates and eliminates variability introduced by live traffic sampling. Amazon Bedrock evaluation jobs also support structured scoring outputs, which can be used to enforce objective quality thresholds.

Integrating evaluation jobs directly into AWS CodePipeline ensures that quality checks are automatically triggered whenever prompt templates or configurations change. This creates a gated deployment workflow in which only configurations that meet or exceed the predefined quality threshold are promoted. This directly satisfies the requirement to prevent low-quality configurations from being deployed.

Human reviewers can be incorporated by reviewing evaluation results and scores produced by the jobs, enabling informed feedback without manual data collection. Option A and D rely on custom frameworks and indirect quality signals, increasing complexity and reducing reliability. Option C focuses on operational health rather than response quality.

Therefore, Option B provides the most robust, scalable, and AWS-aligned quality assurance process for Amazon Bedrock–based applications.

Option A is the correct solution because it relies on native Amazon Bedrock capabilities to deliver transparency, auditability, scalability, and low latency with minimal operational overhead. Amazon Bedrock Knowledge Bases provide a fully managed Retrieval Augmented Generation (RAG) implementation that automatically handles document ingestion, embedding, retrieval, and source attribution, enabling the application to cite authoritative content without building custom pipelines.

Enabling tracing for Amazon Bedrock Agents provides end-to-end visibility into agent reasoning steps, tool usage, and model interactions. This satisfies the requirement for comprehensive audit trails and supports regulatory review in financial services environments. Structured prompts further ensure that responses explicitly present reasoning and supporting evidence in a controlled, auditable format.

Using Amazon API Gateway and AWS Lambda allows the application to scale automatically to thousands of concurrent users without capacity planning. These services are designed for bursty workloads and can easily support the stated requirement of up to 10,000 concurrent users. Amazon CloudFront reduces latency by caching and accelerating content delivery, helping the application meet the strict 2-second response-time requirement.

Option B introduces a custom RAG pipeline with OpenSearch, increasing operational complexity and maintenance effort. Option C lacks native RAG integration and does not provide transparent reasoning or citation management. Option D focuses on offline compliance reporting rather than real-time transparency and low-latency responses.

Therefore, Option A best meets all requirements while minimizing infrastructure and operational overhead.

The correct answers are A and D because they directly reduce time-to-first-token and stabilize p95 latency for interactive, real-time chat workloads hosted on Amazon SageMaker AI real-time endpoints.

Option D addresses the biggest driver of uneven latency: cold starts and scale-to-zero behavior. By setting the minimum number of instances to greater than 0, the endpoint always has warm capacity and loaded runtime resources, eliminating the first-request penalty that causes users to wait multiple seconds. Enabling response streaming improves perceived latency by returning the first tokens as soon as they are generated rather than waiting for the complete response. This directly targets the abandonment problem described (users leaving after waiting for the first token).

Option A further improves p95 latency and throughput by removing model loading overhead during inference and improving GPU utilization. Preloading model weights during container startup ensures the model is ready before traffic arrives and avoids unpredictable on-demand weight loading. Dynamic batching increases efficiency by grouping compatible requests into a single inference pass, reducing per-request overhead and improving GPU saturation. When tuned properly for interactive workloads, batching can reduce tail latency while preserving responsiveness by enforcing small batch windows.

Option B makes latency worse because setting minimum instances to 0 and lazily loading weights guarantees cold-start delays and unpredictable first-token performance. Option C similarly increases cold-start behavior through lazy loading and offers no batching benefits. Option E is designed for non-interactive workloads and introduces queueing and storage latency, which conflicts with the 800 ms p95 requirement for interactive chat.

Therefore, A and D are the best combination to achieve consistently low p95 latency and fast first-token streaming for a SageMaker-hosted chat assistant.

Option B is the best solution because it directly addresses the Step Functions 256 KB state payload quota by externalizing large intermediate artifacts to Amazon S3 and passing only lightweight references (URIs/keys) between states. This is a standard AWS pattern for workflows that produce large intermediate results, and it avoids introducing additional databases, compression logic, or cross-state-machine coordination that increases operational overhead.

In a multi-agent ReAct workflow, intermediate reasoning traces can be verbose and grow quickly as each agent produces chain-of-thought style artifacts, structured outputs, and supporting evidence. Step Functions is designed to orchestrate state transitions and pass JSON payloads, but large payloads should be stored outside the state machine and referenced by pointer values. Using Amazon S3 for intermediate outputs is operationally efficient because the application already uses S3 for storage, and S3 provides durable, low-cost storage with simple access patterns.

ResultPath and ResultSelector allow each state to store or reshape results so that only the required reference fields (such as s3Uri, object key, metadata, trace IDs) are forwarded to subsequent states. This preserves observability because the workflow can still log trace references, correlate steps with S3 objects, and store structured metadata for debugging. It also preserves the sequential validation design, keeping the existing ReAct pattern intact while preventing failures due to oversized payloads.

Option A adds additional services and read/write patterns that increase operational complexity. Option C introduces custom compression/decompression logic that is fragile, adds latency, and complicates troubleshooting. Option D increases orchestration overhead by splitting workflows and coordinating with events, which makes debugging harder and increases failure modes.

Therefore, Option B meets the payload limit requirement while keeping the architecture simple and observable.

The correct answers are B and C because they directly address hallucination reduction while maintaining high throughput and low latency.

Option B reduces hallucinations at their source by grounding model outputs in verified content through Retrieval Augmented Generation (RAG). Using an Amazon Bedrock knowledge base with semantic chunking ensures that long technical documents are broken into meaningfully coherent sections. This allows the model to retrieve only the most relevant chunks, rather than processing an entire document in one pass, which significantly improves factual accuracy and reduces cognitive overload on the model. This approach scales efficiently and supports processing more than 1,000 documents per hour.

Option C adds a defense-in-depth safety layer by using Amazon Bedrock guardrails to detect and block hallucination-like output patterns. Guardrails operate at inference time with minimal performance overhead, making them suitable for low-latency requirements. While guardrails do not eliminate hallucinations entirely, they effectively prevent unsafe or clearly fabricated outputs from reaching users.

Option A increases latency and cost due to explicit reasoning steps and does not scale well for high-throughput workloads. Option D increases randomness and worsens hallucinations. Option E repeats the existing flawed approach.

Therefore, Options B and C together provide scalable grounding and runtime protection that meet accuracy, performance, and throughput requirements.

Option B is the correct solution because it parallelizes independent foundation model inference tasks while maintaining orchestration, observability, and time-bound execution. AWS Generative AI best practices emphasize reducing end-to-end latency by parallelizing independent inference calls rather than scaling individual calls vertically.

In this scenario, each report requires multiple independent analyses such as financial extraction, sentiment analysis, and compliance validation. These tasks do not depend on each other’s output, making them ideal candidates for parallel execution. AWS Step Functions provides a Parallel state that can invoke multiple AWS Lambda functions simultaneously, drastically reducing total processing time compared to sequential execution.

By invoking Amazon Bedrock from separate Lambda functions in parallel, the system can reduce batch execution time from 45 seconds to well under the 10-second requirement, assuming each inference call remains within acceptable latency bounds. Step Functions also provide built-in error handling, retries, and state tracking, which improves reliability without increasing complexity.

CloudWatch metrics allow teams to monitor both workflow execution time and individual model inference latency, enabling performance tuning and operational visibility. Configuring client-side timeouts ensures that slow or failed model invocations do not block the entire batch.

Option A still processes tasks sequentially and therefore cannot meet the strict latency requirement. Option C introduces queuing delays and sequential processing within each report, which increases total execution time. Option D relies on container-based sequential processing and adds unnecessary operational overhead for a workload that is event-driven and latency-sensitive.

Therefore, Option B best meets the performance, scalability, and operational efficiency requirements for high-speed batch document analysis using Amazon Bedrock.

This error occurs because SCPs override IAM permissions, and the SCP currently blocks Bedrock inference calls that resolve to eu-west-3, even though the company intends to use cross-Region inference (CRI) from eu-central-1.

Amazon Nova Pro is not hosted in eu-central-1, so when invoked, Amazon Bedrock transparently routes the request to a supporting Region (such as eu-west-3) through CRI inference profiles. However, SCPs that restrict Regions or specific Bedrock resources will block this routing unless explicitly allowed.

Option B is required because the SCP must explicitly allow the eu.amazon.nova-pro-v1:0 inference profile, which is the Bedrock abstraction that enables CRI while preserving data residency guarantees. Without this, Bedrock cannot legally route the request.

Option E is also required to allow EU-scoped inference profiles rather than individual Regions. This preserves precise governance while allowing Bedrock-managed CRI routing within the EU boundary, ensuring no data leaves Europe.

Option A violates least-privilege and does not override SCPs. Option C breaks data residency by enabling direct eu-west-3 access. Option D does not resolve the SCP denial.

Therefore, Options B and E are the only combination that resolves the error while preserving governance and EU-only data residency.

Option A is the correct solution because hybrid search directly addresses the core retrieval failure modes while maintaining low latency and minimal operational overhead. In medical and scientific domains, exact terminology, abbreviations, and acronyms (for example, drug names, procedures, or conditions) are critical. Pure vector similarity search often underweights these exact matches, leading to missed results and excessive semantically related but irrelevant documents.

Amazon OpenSearch Service natively supports hybrid search, which combines keyword-based retrieval (such as BM25) with vector similarity search. Keyword search ensures precise matching for exact terms and acronyms, while vector search captures semantic meaning and contextual similarity. By blending these approaches, the retrieval system improves both precision and recall without introducing additional infrastructure.

Hybrid search operates within the same OpenSearch index and query path, which preserves low end-user latency even at large scale. This is especially important as the document collection grows to millions of documents. Because OpenSearch handles scoring and ranking internally, no additional orchestration layers or post-processing steps are required.

Option B increases computational cost and latency while failing to address exact-term recall. Option C introduces a new service and ingestion pipeline, increasing operational overhead and latency. Option D adds model hosting, re-ranking infrastructure, and complexity that is unnecessary when OpenSearch provides native hybrid retrieval.

Therefore, Option A delivers the best balance of retrieval quality, scalability, latency, and operational simplicity for medical RAG workloads.

Option C directly addresses the root cause of truncated and inconsistent responses by using AWS-recommended semantic chunking and dynamic retrieval rather than static or sequential chunk processing. Amazon Bedrock documentation emphasizes that foundation models have fixed context windows and that sending oversized or poorly structured input can lead to truncation, loss of context, and degraded output quality.

Semantic chunking breaks documents based on meaning instead of fixed token counts. By using a breakpoint percentile threshold and sentence buffers, the content remains coherent and semantically complete. This approach reduces the likelihood that important concepts are split across chunks, which is a common cause of inconsistent summarization results.

The RetrieveAndGenerate API is designed specifically to handle large documents that exceed a model’s context window. Instead of forcing all content into a single inference call, the API generates embeddings for chunks and dynamically selects only the most relevant chunks based on similarity to the user query. This ensures that the FM receives only high-value context while staying within its context window limits.

Option A is ineffective because chaining chunks sequentially does not align with how FMs process context and risks exceeding context limits or introducing irrelevant information. Option B improves structure but still relies on larger parent chunks, which can lead to inefficiencies when processing very large documents. Option D processes segments independently, which often causes loss of global context and inconsistent summaries.

Therefore, Option C is the most robust, AWS-aligned solution for resolving truncation and consistency issues when processing large technical documents with Amazon Bedrock.

Option A is the correct solution because it directly addresses all identified failure modes while preserving the existing Step Functions–based orchestration architecture with minimal redesign.

Using Step Functions Map states enables parallel execution of secret resolution workflows, which improves refresh latency for short-lived and expiring secrets. This ensures that secrets are refreshed in time before downstream agents require them. Passing updated secret metadata through Lambda outputs guarantees that subsequent steps always consume the latest resolved values, preventing agents from using stale data even after drift alerts are generated.

Versioning prompt flows in AWS AppConfig is critical to resolving cascading failures caused by outdated templates. AppConfig natively supports version control, validation, staged rollout, and rollback of configuration artifacts. By gating prompt flows through AppConfig, the company can immediately roll back faulty templates and prevent agents from reusing outdated instructions.

This solution maintains clear separation of concerns: Step Functions handle orchestration and parallelism, Lambda handles secret retrieval and metadata propagation, and AppConfig governs prompt lifecycle management. No additional event pipelines or custom retry coordination layers are required.

Option B oversimplifies the architecture and does not address secret lifecycle or drift. Option C introduces event-driven ordering complexity without solving prompt versioning. Option D introduces unnecessary tooling and dynamic prompt generation risk.

Therefore, Option A best resolves performance, correctness, and stability issues while minimizing operational overhead.

Option D is the correct solution because it directly addresses all three requirements: high retrieval accuracy, hallucination detection, and reduced human review costs. AWS recommends a layered evaluation strategy for high-stakes domains such as healthcare, where generative outputs must be both accurate and safe.

Using an automated LLM-as-a-judge evaluation enables scalable, consistent assessment of generated responses for factual grounding, relevance, and hallucination risk. This automated screening significantly reduces the number of responses that require manual inspection. Only responses that fall below defined quality thresholds or exhibit ambiguous behavior are escalated to targeted human reviews, which optimizes review effort and cost.

The use of Amazon Bedrock built-in evaluations provides standardized metrics specifically designed for RAG systems, including retrieval precision, faithfulness to source documents, and hallucination rates. These evaluations integrate directly with Amazon Bedrock knowledge bases and models, eliminating the need to build and maintain custom evaluation pipelines.

Option A focuses on entity extraction confidence, which does not reliably detect hallucinations in generative text. Option B requires maintaining and scaling a separate fine-tuned evaluation model, increasing complexity and cost. Option C is useful for regression testing but cannot detect hallucinations in real-world, open-ended clinical queries.

Therefore, Option D provides the most effective and operationally efficient approach to maintaining clinical-grade accuracy while minimizing human review effort.

Option A best meets the requirements because it directly implements a Retrieval Augmented Generation pattern for conversational recommendations using managed Amazon Bedrock capabilities and a scalable vector store. The company’s source data already resides in Amazon S3, which aligns naturally with Amazon Bedrock Knowledge Bases ingestion workflows. A knowledge base can ingest book text, reviews, and metadata, generate embeddings using a supported embedding model, and persist those vectors in a purpose-built vector backend such as Amazon OpenSearch Service. This enables semantic retrieval that is well suited to conversation-driven intent, where user prompts are often descriptive and do not map cleanly to keyword filters.

The requirement to suggest books based on conversations implies the system must interpret natural language context and retrieve relevant passages, reviews, and metadata to ground the recommendation. Knowledge Bases provide managed orchestration for embedding creation and retrieval, which reduces development effort compared to building custom embedding pipelines. OpenSearch Service provides scalable vector search and k-nearest neighbors style similarity retrieval, which supports low-latency responses when properly indexed and sized.

For scaling to more than 10,000 concurrent users, the API layer design in option A is a common AWS pattern: Amazon API Gateway provides a managed front door with throttling and request handling, while AWS Lambda scales horizontally with demand and can invoke the knowledge base retrieval operations. This separates compute scaling from the vector store scaling and helps keep latency predictable under load.

Option B is not the best choice because DynamoDB is not the standard native vector store target for Amazon Bedrock Knowledge Bases in this context and would introduce additional implementation complexity around vector indexing and similarity search behavior. Option C requires substantial ML lifecycle work, model hosting, tuning, and continuous iteration to achieve quality recommendations at scale. Option D provides strong enterprise search, but it focuses on retrieval and FAQs rather than a managed RAG recommendation workflow grounded in embeddings and conversational context for generative responses.

Option A best meets the combined requirements of low latency, stability, and validated safety controls by using purpose-built Amazon Bedrock features designed for production GenAI operations. The company’s latency target of under 1 second and its observation of degradation during spikes strongly indicate capacity and throughput variability. Provisioned throughput for Amazon Bedrock is intended to deliver more predictable performance by reserving inference capacity for a chosen model, reducing throttling risk and stabilizing response times under load. This directly improves operational consistency across Regions where on-demand capacity can vary.

The requirement to “block unsafe or hallucinated recommendations” is most directly addressed by Amazon Bedrock Guardrails. Guardrails provide managed safety enforcement, including sensitive information controls and configurable content policies. Using semantic denial rules enables the application to prevent unsafe guidance such as dangerous brewing temperatures or other harmful procedural instructions, enforcing safety at the model boundary rather than relying on downstream filtering.

The remaining requirement is “99.5% output consistency for identical inputs.” While generative models can be probabilistic, production systems achieve practical consistency by controlling prompt versions, inputs, and policy behavior. Amazon Bedrock Prompt Management supports controlled prompt lifecycle practices, including versioning and approval workflows, which reduce unintended drift across deployments and Regions. By ensuring the same approved prompt templates and parameters are used consistently, the company can materially improve repeatability for the same structured inputs and retrieval context, which is essential in multi-stage prompt chains.

The other options are incomplete. B improves experimentation and observability but does not enforce safety controls or stabilize latency. C can improve performance, but it does not provide validated safety enforcement at inference time. D can help retrieval relevance, but it does not address unsafe outputs or inference stability. Therefore, A is the only option that simultaneously targets predictable latency, governance of prompt behavior, and strong safety controls within Amazon Bedrock.

Option C is the correct solution because it directly addresses the root cause of the problem—overly broad retrieval—while requiring minimal architectural change. Amazon Bedrock Knowledge Bases support metadata-aware filtering, which allows the system to constrain retrieval queries based on indexed metadata such as content type, publication date, source, or category.

By indexing Amazon S3 object metadata, the company can restrict vector searches to relevant subsets of the corpus, such as recent emergency reports, specific content formats, or trusted sources. This significantly reduces the number of documents evaluated during retrieval, which improves both latency and result relevance without changing embedding models or retrieval infrastructure.

This approach aligns with AWS best practices for optimizing RAG systems: when embeddings are already strong, retrieval quality is often improved by narrowing the candidate set rather than increasing model complexity. Metadata filtering reduces noise and ensures that retrieved documents are more contextually aligned with user queries.

Option A requires retraining or adapting embedding models, which the company has already determined will not provide additional benefit. Option B introduces a migration to OpenSearch, which adds operational overhead and deviates from the existing Bedrock knowledge base architecture. Option D requires moving to a different indexing service, increasing complexity and implementation effort.

Therefore, Option C provides the most effective and low-effort solution to improve retrieval accuracy and performance in the existing Amazon Bedrock RAG system.

Option A best meets the requirements because it applies an AWS-aligned multi-agent pattern that cleanly separates responsibilities: a supervisor agent performs intent classification and orchestration, while specialized collaborator agents handle domain-specific tasks using the right knowledge sources. This structure is well suited for healthcare workflows where clinical questions, scheduling, and insurance processes require different policies, terminology, and data access boundaries.

The requirement for appropriate domain-specific responses is addressed by routing each user query to a department-focused collaborator agent that is grounded with its own department-specific knowledge base. Using Retrieval Augmented Generation with the correct knowledge base improves factual alignment and reduces cross-department leakage (for example, avoiding claims content in a clinical answer). It also supports better prompt grounding and more consistent tone and constraints per department.

The requirement to isolate data maps to using separate knowledge bases per agent and enforcing access through IAM controls, ensuring that each agent can retrieve only from the authorized datasets. This is important for minimizing unintended exposure of sensitive or irrelevant departmental data and supports governance and compliance needs.

For scalability and thousands of parallel interactions, this architecture minimizes contention and bottlenecks. Each collaborator agent can scale independently because requests are distributed across multiple agents and multiple retrieval backends. Operationally, onboarding new features is also simpler: the company can add a new collaborator agent (for example, “billing disputes” or “pharmacy refills”) with its own knowledge base and policies without redesigning the entire assistant.

Option B introduces unnecessary complexity with multiple supervisors and manual handoffs. Option C overloads a single agent with broad instructions and rule-based routing, which increases prompt complexity and reduces maintainability as features grow. Option D creates high operational complexity and risks inconsistent outputs when merging responses from parallel supervisors, and it weakens data isolation by using a shared knowledge base across agents.

This requirement explicitly calls for character-by-character streaming, long-running responses, low latency, and massive concurrency, which aligns directly with Amazon Bedrock streaming inference patterns.

Amazon Bedrock provides the InvokeModelWithResponseStream API specifically for streaming partial model outputs as tokens are generated. This enables near-instant feedback to users instead of waiting for the full response to complete, which is essential when responses last up to 45 seconds.

Amazon API Gateway WebSocket APIs are purpose-built for bidirectional, low-latency, server-initiated communication, allowing the backend to push characters or tokens to clients in real time. This eliminates inefficient polling and supports thousands of concurrent open connections.

AWS Lambda integrates natively with WebSocket APIs and scales automatically with connection volume, enabling a fully managed, serverless architecture. This approach maintains security, centralized authentication, throttling, and observability while avoiding direct client access to Bedrock APIs.

Option B introduces polling latency and unnecessary API overhead and does not provide true streaming. Option C violates AWS security best practices by exposing Bedrock directly to clients and does not scale securely. Option D only serves completed responses and cannot meet the real-time streaming requirement.

Therefore, Option A is the only solution that fully satisfies streaming behavior, concurrency, latency, and managed-service constraints.

The correct combination is A, B, and D because these three options collectively satisfy the mandatory requirements for structured extraction, PII redaction before inference, regional human review, data residency, auditability, and high-scale availability with managed AWS services.

Option A is essential because Amazon Textract is the AWS-managed service designed to extract structured data from scanned documents such as forms, tables, and financial statements. Textract provides confidence scores, and Amazon Augmented AI (A2I) is purpose-built to route low-confidence extractions to human reviewers. Deploying Textract and A2I within the same Region ensures that the human review loop remains regionally constrained, meeting strict data residency requirements for applicants.

Option B satisfies the requirement to redact PII before inference by using AWS Lambda preprocessing. It also adds Amazon Bedrock guardrails to enforce safety controls on model outputs. Region-specific IAM roles ensure that only authorized principals in the correct Region can access the extracted data and invoke downstream services, strengthening residency enforcement and auditability.

Option D ensures that source documents are stored in Amazon S3 in the same Region as the applicant. Object metadata and tagging provide an auditable trail, supporting compliance reporting and traceability. S3 also provides the durability and availability needed to support 99.9% application availability as part of a well-architected pipeline.

Option C is not the correct approach for structured extraction from scans. Option E adds useful quality validation but is not strictly required to meet the stated requirements compared to A, B, and D. Option F is unrelated to the extraction/redaction/residency workflow requirements.

Therefore, A, B, and D are the best three choices to meet all stated requirements with minimal operational overhead.

Option D is the correct solution because it directly satisfies all three core requirements: data source registration, metadata-based attribution, and end-to-end audit logging, while remaining service-agnostic and scalable across internal and external data sources.

The AWS Glue Data Catalog is the AWS-native service for registering datasets and managing metadata centrally. It supports structured registration of diverse data sources and enables consistent tagging that can be used to attribute generated content back to its original source. This is essential for GenAI applications that combine multiple datasets and must provide traceability for outputs.

Metadata tags applied within the Glue Data Catalog ensure a consistent attribution framework that downstream systems—such as Retrieval Augmented Generation (RAG) pipelines or evaluation systems—can reference without embedding attribution logic directly in application code. This improves maintainability and governance.

AWS CloudTrail provides immutable audit logs of API activity across AWS services, including data access, metadata changes, and pipeline interactions. CloudTrail logs are critical for compliance and regulatory review because they capture who accessed which data, when, and through which service. This satisfies the requirement to maintain audit logs “throughout the pipeline,” not just at storage or application layers.

Option A introduces Lake Formation, which is primarily intended for fine-grained data lake permissions and is not required solely for traceability. Option B relies on CloudWatch Logs, which does not provide authoritative audit logging across services. Option C limits audit scope to S3 access and does not register or govern all data sources comprehensively.

Therefore, Option D provides the most complete and least intrusive solution for traceable, auditable GenAI data pipelines.

Option C is the correct solution because AWS AppConfig is purpose-built to manage dynamic application configurations with low latency, strong validation, and minimal operational overhead, which directly matches the company’s requirements.

AWS AppConfig enables the company to centrally manage model selection logic, inference parameters, and customer-tier routing rules without redeploying Lambda functions. By using feature flags, the company can easily perform A/B testing of new models or prompt strategies by gradually rolling out changes to a subset of users or customer tiers. This allows experimentation and controlled releases without code changes.

AppConfig also supports JSON schema validation, which is critical for validating parameters such as temperature, maximum token limits, and other model-specific settings before they are applied. This prevents invalid or unsafe configurations from being deployed and reduces the risk of runtime errors or degraded model behavior in production.

Using the AWS AppConfig Agent allows Lambda functions to retrieve configurations efficiently with built-in caching and polling mechanisms, minimizing latency and avoiding excessive calls to configuration services. This approach scales well for high-throughput, low-latency applications such as GenAI APIs behind Amazon API Gateway.

Option A introduces unnecessary redeployment logic and polling complexity. Option B requires building and maintaining custom configuration access patterns in DynamoDB and does not natively support feature flags or schema validation. Option D adds operational overhead by requiring ElastiCache cluster management and custom validation logic.

Therefore, Option C provides the most scalable, flexible, and low-maintenance solution for dynamic model switching, A/B testing, and safe configuration management in a GenAI application.

Option B is the correct solution because it leverages native Amazon Bedrock intelligent prompt routing, which is specifically designed to reduce cost and complexity in multi-model GenAI architectures. Intelligent prompt routing automatically analyzes incoming prompts and selects the most appropriate foundation model based on prompt characteristics and complexity—without requiring custom classification logic or orchestration code.

This approach directly meets the requirement for least implementation effort. The company does not need to deploy additional Lambda functions, maintain routing rules, or manage separate classification stages. Routing decisions are handled by Bedrock, which simplifies architecture and reduces operational risk.

By routing the majority (70%) of simple product inquiries to smaller, lower-cost models, the company minimizes inference cost and latency. More complex return policy inquiries are automatically routed to larger models that provide better reasoning capabilities, preserving response quality and customer satisfaction.

Because routing is handled inline by Bedrock, response latency remains low compared to multi-stage architectures that require an additional classification model call before inference. This is critical for customer service scenarios where responsiveness directly impacts satisfaction.

Option A introduces additional inference steps and custom logic. Option C increases cost by overusing a mid-sized model for all queries. Option D relies on brittle keyword rules and increases operational overhead through endpoint management.

Therefore, Option B delivers the optimal balance of cost efficiency, performance, and simplicity for dynamic model selection in Amazon Bedrock.