AWS Bedrock Guardrails

Creating a Policy

After you have selected AWS Bedrock Guardrails as your AI firewall provider:

Step 1: Select Mapped Probes

Only probes that meet the required criteria are shown, and their fail rates are displayed for reference.

Probes used in this step must:

• Have a completed probe run.

• Have mapped Policy Rules.

These criteria ensure that only relevant probes are included in the generated policy, keeping configurations accurate and efficient.

Figure 1: Select Mapped Probes

Generated Policy Template Page

Once the new policy has been generated, the Generated Policy Template Page displays the full details of the result.

The top section includes key policy information:

• AI Firewall Provider - AI firewall provider for which the policy was generated.

• Generated on - when the policy was generated.

• Generated by - who generated the policy.

• Selected probes - probes used to create a template based on the results of their runs.

• Progress - showing whether the policy template is being generated or the generation is finished.

Below the summary of the latest generated policy, users can interact with two key sections:

1. CLI Command: A pre-generated AWS CLI command for provisioning a Bedrock guardrail using create-guardrail with a predefined JSON configuration. This command simplifies the process of applying guardrails to an AI runtime environment.

2. JSON Formatted Policy: A detailed JSON configuration that outlines the rules and settings for the Bedrock guardrail. It includes predefined values for fields such as names, blocked input/output messages, and other policy configurations, which users can directly use.

Figure 2: Latest Generated Policy Template page for AWS Bedrock Guardrails