Tools · Question 5 of 12
Which AWS tool filters harmful content in the inputs and outputs of generative AI?
1 answer is correct. Easy
Show answer
Answer
- A Amazon Bedrock Guardrails
Explanation
Bedrock Guardrails offers content filters for hate, insults, sexual content, violence and misconduct, as well as denied topics, sensitive information filters and checks for hallucinations. This is how responsible AI policies are implemented technically.