AWS Certified AI Practitioner (AIF-C01) — Question 278

An ecommerce company is deploying a chatbot. The chatbot will give users the ability to ask questions about the company’s products and receive details on users’ orders. The company must implement safeguards for the chatbot to filter harmful content from the input prompts and chatbot responses.

Which AWS feature or resource meets these requirements?

Answer options

• A. Amazon Bedrock Guardrails
• B. Amazon Bedrock Agents
• C. Amazon Bedrock inference APIs
• D. Amazon Bedrock custom models

Correct answer: A

Explanation

Amazon Bedrock Guardrails allows organizations to implement customized safeguards to block undesirable or harmful content in both user inputs and model outputs. Amazon Bedrock Agents are used to automate multi-step tasks, while inference APIs are used to run model queries, and custom models are for fine-tuning base models on specific domain data. None of these other features natively provide the content filtering capabilities of Guardrails.