AWS Certified Generative AI – Professional (AIP-C01) — Question 40

A financial services company is developing a real-time generative AI (GenAI) assistant to support human call center agents. The GenAI assistant must transcribe live customer speech, analyze context, and provide incremental suggestions to call center agents while a customer is still speaking. To preserve responsiveness, the GenAI assistant must maintain end-to-end latency under 1 second from speech to initial response display. The architecture must use only managed AWS services and must support bidirectional streaming to ensure that call center agents receive updates in real time.
Which solution will meet these requirements?

Answer options

• A. Use the Amazon Transcribe streaming API to transcribe calls. Pass the text to Amazon Comprehend to perform sentiment analysis. Feed the results to Anthropic Claude on Amazon Bedrock by using the InvokeModel API. Store results in Amazon DynamoDB. Use a WebSocket API to display the results.
• B. Use Amazon Transcribe streaming with partial results enabled to deliver fragments of transcribed text before customers finish speaking. Forward text fragments to Amazon Bedrock by using the InvokeModelWithResponseStream API. Stream responses to call center agents through an Amazon API Gateway WebSocket API.
• C. Use Amazon Transcribe batch processing to convert calls to text. Pass complete transcripts to Anthropic Claude on Amazon Bedrock by using the ConverseStream API. Return responses through an Amazon Lex chatbot interface that call center agents can access from their work computers.
• D. Use the Amazon Transcribe streaming API with an AWS Lambda function to transcribe each audio segment. Configure the Lambda function to call the Amazon Titan Embeddings model on Amazon Bedrock by using the InvokeModel API. Configure the Lambda function to publish results to an Amazon SNS topic. Subscribe the call center agents to the SNS topic.

Correct answer: B

Explanation

Option B is the correct answer because it uses Amazon Transcribe streaming with partial results, enabling real-time transcription and immediate feedback to agents. The other options either do not meet the latency requirement, use batch processing which is not suitable for real-time needs, or involve architectures that do not support the necessary bidirectional streaming.