Updated Amazon AIP-C01 Exam Dumps (July, 2026)

AWS Certified Generative AI Developer - Professional

Question 1

A company is developing three specialized NLP models that support a customer service application. One model categorizes each customer’s specific issue. Another model extracts key information from the customer interactions. The third model generates responses. The company must ensure that the application achieves at least 95% accuracy for all tasks. The application must handle up to 500 concurrent requests and respond in less than 500 ms during daily 2-hour peak usage periods. The company must ensure that the application optimizes resource usage during periods of low demand between usage spikes. Which solution will meet these requirements?

A. Deploy all three models to a single Amazon SageMaker AI multi-model endpoint. Enable dynamic scaling on the endpoint. Use a compute optimized instance type. Configure auto scaling policies that are based on invocation metrics to handle peak loads. 
B. Deploy each model to a separate Amazon SageMaker Serverless Inference endpoint. Set provisioned concurrency to handle peak loads. Configure maximum concurrency limits and memory sizing based on each model's specific requirements. 
C. Deploy the models by using Amazon Bedrock with provisioned throughput to handle peak loads. Configure the number of model units (MUs) based on expected token throughput needs. Implement request batching for each model. 
D. Deploy each model to a separate Amazon SageMaker AI endpoint. Use an asynchronous inference configuration. Store model requests and responses in Amazon S3. Use Amazon SNS to send alerts to users when the application finishes processing requests. 

Answer: B

Question 2

A financial services company is developing an AI-powered search assistant application to help investment advisors quickly retrieve investment data. The application runs as an AWS Lambda function. The company is using Amazon Bedrock to develop the application by using an Amazon Bedrock knowledge base that uses 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. The company uses Amazon Bedrock tools to test the knowledge base. The knowledge base sync process finishes successfully. However, the test reveals a 400 Bad Authorization error from the BedrockAgentRuntime API and a 403 Forbidden error when the test attempts to access OpenSearch Serverless. The company must resolve the permissions issues. Which combination of solutions will meet this requirement? (Select TWO.)

A. Update the Lambda function execution role to include the bedrock:InvokeAgent permission. Add the aoss:APIAccessAll permission to the Lambda execution role. 
B. Create an OpenSearch Serverless data access policy that includes pattern-based resource rules. 
C. Configure a VPC endpoint policy for OpenSearch Serverless. Add the endpoint to the Lambda function's VPC configuration. 
D. Configure AWS Secrets Manager to store OpenSearch Serverless credentials. Grant the Lambda function access to retrieve the credentials. 
E. Enable IAM authentication for the OpenSearch Serverless domain. Add the es:ESHttp* permission to the Lambda function execution role. 

Answer: A,B

Question 3

A company is using Amazon Bedrock to develop an AI-powered application that uses a foundation model (FM) that supports cross-Region inference and provisioned throughput. The application must serve users in Europe and North America with consistently low latency. The application must comply with data residency regulations that require European user data to remain within Europe-based AWS Regions. During testing, the application experiences service degradation when Regional traffic spikes reach service quotas. The company needs a solution that maintains application resilience and minimizes operational complexity. Which solution will meet these requirements?

A. Deploy separate Amazon Bedrock instances in North American and European Regions. Use a custom routing layer that directs traffic based on user location. Configure Amazon CloudWatch alarms to monitor Regional service usage. Use Amazon SNS to send email alerts when usage approaches thresholds. 
B. Use Amazon Bedrock cross-Region inference profiles by specifying geographical codes in profile IDs when calling the InvokeModel API. Configure separate Amazon API Gateway HTTP APIs to direct European and North American users to the appropriate Regional endpoints. 
C. Deploy a multi-Region Amazon API Gateway HTTP API and AWS Lambda functions that implement retry logic to handle throttling. Configure the Lambda functions to call the FM in the nearest secondary Region when quotas are reached. 
D. Configure provisioned throughput for Amazon Bedrock in multiple Regions. Implement failover logic in application code to switch Regions when throttling occurs. Use AWS Global Accelerator to route traffic based on user location. 

Answer: B

Question 4

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). The application uses AWS Lambda functions to retrieve secrets from the sources. The application uses AWS AppConfig to implement dynamic feature gating. The application supports secret chaining and detects secret drift. The application handles short-lived and expiring secrets. The application also supports prompt flows for templated instructions. The application uses AWS Step Functions to orchestrate agents to resolve the secrets and to manage secret validation and drift detection. The company finds multiple issues during application testing. The application does not refresh expired secrets in time for agents to use. The application sends alerts for secret drift, but agents still use stale data. Prompt flows within the application reuse outdated templates, which cause cascading failures. The company must resolve the performance issues. Which solution will meet this requirement? 

A. Use Step Functions Map states to run agent workflows in parallel. Pass updated secret metadata through Lambda function outputs. Use AWS AppConfig to version all prompt flows to gate and roll back faulty templates. 
B. Use Amazon Bedrock Agents only. Configure Amazon Bedrock guardrails to restrict prompt variation. Use an inline JSON schema for a single agent’s workflow definition to chain tool calls. 
C. Use a centralized Amazon EventBridge pipeline to invoke each agent. Store intermediate prompts in Amazon DynamoDB. Resolve agent ordering by using TTL-based backoff and retries. 
D. Use Amazon EventBridge Pipes to invoke resolvers based on Amazon CloudWatch log patterns. Store response metadata in DynamoDB with TTL and versioned writes. Use Amazon Q Developer to dynamically generate fallback prompts. 

Answer: A

Question 5

A company is designing a solution that uses foundation models (FMs) to support multiple AI workloads. Some FMs must be invoked on demand and in real time. Other FMs require consistent high-throughput access for batch processing. The solution must support hybrid deployment patterns and run workloads across cloud infrastructure and on-premises infrastructure to comply with data residency and compliance requirements. Which combination of steps will meet these requirements? (Select TWO.)

A. Use AWS Lambda to orchestrate low-latency FM inference by invoking FMs hosted on Amazon SageMaker AI asynchronous endpoints. 
B. Configure provisioned throughput in Amazon Bedrock to ensure consistent performance for high-volume workloads. 
C. Deploy FMs to Amazon SageMaker AI endpoints with support for edge deployment by using Amazon SageMaker Neo. Orchestrate the FMs by using AWS Lambda to support hybrid deployment. 
D. Use Amazon Bedrock with auto-scaling to handle unpredictable traffic surges. E. Use Amazon SageMaker JumpStart to host and invoke the FMs. 

Answer: B,C