AWS Certified Generative AI – Professional (AIP-C01) — Question 66

A retail company is using Amazon Bedrock to develop a customer service AI assistant. Analysis shows that 70% of customer inquiries are simple product questions that a smaller model can effectively handle. However, 30% of inquiries are complex return policy questions that require advanced reasoning. The company wants to implement a cost-effective model selection framework to automatically route customer inquiries to appropriate models based on inquiry complexity. The framework must maintain high customer satisfaction and minimize response latency.
Which solution will meet these requirements with the LEAST implementation effort?

Answer options

• A. Create a multi-stage architecture that uses a small foundation model (FM) to classify the complexity of each inquiry. Route simple inquiries to a smaller, more cost-effective model. Route complex inquiries to a larger, more capable model. Use AWS Lambda functions to handle the routing logic.
• B. Use Amazon Bedrock intelligent prompt routing to automatically analyze inquiries. Route simple product inquiries to smaller models, and route complex return policy inquiries to more capable larger models.
• C. Implement a single-model solution that uses an Amazon Bedrock mid-sized foundation model (FM) with on-demand pricing. Include special instructions in model prompts to handle both simple and complex inquiries by using the same model.
• D. Create separate Amazon Bedrock endpoints for simple and complex inquiries. Implement a rule-based routing system based on keyword detection. Use on-demand pricing for the smaller model and provisioned throughput for the larger model.

Correct answer: B

Explanation

Option B is the best solution as it utilizes Amazon Bedrock's intelligent prompt routing to efficiently analyze and route inquiries based on complexity, achieving the goal with minimal implementation effort. Option A requires building a multi-stage architecture which adds complexity, while Option C attempts to address both inquiries with a single model, potentially compromising performance. Option D involves creating separate endpoints and a rule-based system, which could introduce unnecessary complexity and overhead.