Skip to main content

Create a Safety Policy

Safety policies in DynamoGuard can be used to detect user-provided inputs or model responses that contain unsafe content. See the Safety page in Key Concepts for more details on the Safety policy.

1. Select Policy Type​

After selecting the Safety policy option, determine whether the policy should be applied to user inputs or model responses.

Safety Policy Setup

2. Select a Moderation Behavior​

Choose the moderation behavior for your policy. Safety policies support two behaviors:

  • Flag: flag content for moderator review
  • Block: block user inputs or model outputs containing unsafe content

3. Provide Policy Information​

Provide a policy name and description. These fields help you identify the policy in the future but do not affect its functionality.

Toxicity Policy Setup

4. Finalize and Create your Policy​

Once you’ve completed the setup, click Create Policy. The newly created policy will appear in your Policy Dashboard, where you can manage and track all your policies.

Last updated on