Skip to main content

Create a PII Detection Policy

PII Detection policies in DynamoGuard can be used to detect sensitive PII in user-provided inputs or model responses. See the PII Detection page in Key Concepts for more details on the PII Detection policy.

1. Select Policy Type​

After selecting the PII Detection policy option, determine whether the policy should be applied to user inputs or model responses. Note: policies with behavior sanitize must be applied to inputs and responses.

2. Select a Moderation Behavior​

Choose the moderation behavior for your policy. PII Detection policies support four behaviors:

  • Flag: Flag content for moderator review
  • Block: Block user inputs or model outputs containing PII
  • Redaction: Redact PII before passing user inputs to the model or before displaying outputs to users.
  • Sanitize: Anonymize PII before passing user inputs to the model and de-anonymize PII before displaying outputs to users

PII Policy Setup

3. Select PII Categories​

Provide a policy title and select the PII categories the policy should detect. PII categories can be selected from Dynamo AI’s out-of-the-box supported categories. Additional PII categories can be specified using regular expressions or blocklist entities.

PII 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