{"id":"amazon-bedrock-guardrails","name":"Amazon Bedrock Guardrails","maker":"Amazon Web Services","url":"https://aws.amazon.com/bedrock/guardrails/","docs":"https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html","summary":"An AWS service that filters model inputs and outputs for harmful content, prompt attacks, sensitive data and ungrounded answers.","details":"A guardrail combines content filters including a prompt attack category, denied topics, word filters, sensitive information masking, contextual grounding checks and Automated Reasoning checks. It is applied during Bedrock model calls or on any text through the ApplyGuardrail API. It needs an AWS account and is not open source.","open_source":false,"hosted":true,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/amazon-bedrock-guardrails","reviewed":"2026-11-15","checked":{"at":"2026-11-15T13:03:28.711Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}