Question
A finance company is developing an AI assistant to help clients plan investments and manage their portfolios. The company identifies several high-risk conversation patterns such as requests for specific stock recommendations or guaranteed returns. High-risk conversation patterns could lead to regulatory violations if the company cannot implement appropriate controls.
The company must ensure that the AI assistant does not provide inappropriate financial advice, generate content about competitors, or make claims that are not factually grounded in the company's approved financial guidance. The company wants to use Amazon Bedrock Guardrails to implement a solution.
Which combination of steps will meet these requirements? (Choose three.)
- A. Add the high-risk conversation patterns to a denied topics guardrail. Correct
- B. Configure a content filter guardrail to filter prompts that contain the high-risk conversation patterns.
- C. Configure a content filter guardrail to filter prompts that contain competitor names.
- D. Add the names of competitors as custom word filters. Set the input and output actions to block. Correct
- E. Set a low grounding score threshold.
- F. Set a high grounding score threshold. Correct
Explanation
Option A is correct because adding high-risk conversation patterns to a denied topics guardrail ensures that these patterns are not addressed by the AI assistant. Option D is correct as it involves blocking competitor names both in input and output actions through custom word filters, preventing any content generation about competitors. Option F is correct since setting a high grounding score threshold ensures that responses are factually grounded based on the company's approved financial guidance, thus avoiding inappropriate advice.
