For a description of what compliance category filtering does and why it exists, see Precursive AI Data Privacy and Security. 

Background

Salesforce allows fields to be tagged with compliance categories at the field level: PII, HIPAA, GDPR, PCI, CCPA, and COPPA. By default, Precursive AI strips any field carrying one of these tags from the AI context before it is sent to the LLM. This is the secure default - no compliance-categorised data flows through unless you explicitly allow it.

The compliance category tags themselves are a standard Salesforce feature, managed in Salesforce Setup. Precursive AI reads those tags and applies your Data Privacy configuration at runtime.

Configuring Allowed Compliance Categories

1. Go to Precursive AI Settings via the App Launcher or Precursive HQ
2. Open the Data Privacy tab
3. The dual-listbox shows all six compliance categories (CCPA, COPPA, GDPR, HIPAA, PCI, PII). By default all are listed as Blocked
4. Move any categories to the Allowed list that your organisation's policy permits to be included in AI context
5. Click Save

Important Rules

• If a field is tagged with multiple compliance categories (for example, both PII and HIPAA), it is only included if all of its categories are on the Allowed list. A single non-allowed category causes the field to be stripped.
• If all six categories are moved to the Allowed list, compliance stripping is skipped entirely.
• The filtering runs server-side at context build time and cannot be bypassed from the client.

When to Adjust This Setting

Most organisations should leave the default in place (all categories blocked) unless there is a specific business need to include compliance-categorised fields in AI analysis. Before allowing a category, confirm with your compliance, legal, or InfoSec team that it is appropriate to send that data class to AI sub-processors. See Precursive AI Data Privacy and Security for the full picture of what those sub-processors do with the data.