QuestionQ112

Guidelines for Responsible AI

A social media company wants to stop users from posting discriminatory content on the company’s application. The company wants to use Amazon Bedrock as part of the solution.

How can the company use Amazon Bedrock to satisfy these requirements?

  • A Give users the ability to interact based on user preferences.
  • B Block interactions related to predefined topics.
  • C Restrict user conversations to predefined topics.
  • D Provide a variety of responses to select from for user engagement.
Explanation

Amazon Bedrock Guardrails can filter harmful user inputs and model outputs. Its content filters include a Hate category for content that discriminates against, insults, or dehumanizes people or groups based on protected identity characteristics; guardrails can also block configured denied topics.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!