Add an AI Guardrails Rule to the Data Loss Prevention Policy
AI guardrails rules operate within the data loss prevention policy to monitor prompts, responses, and files embedded in prompts exchanged with AI applications. The rules define what types of data to monitor, and whether content should be blocked or only monitored.
An AI Guardrails rule must have at least one of the following two criteria defined:
- Data Classifications — Include files that match data classification of your own making or a built-in data classification provided by Secure Access.
- File Size — Include files that meet custom size criteria.