Jun 16, 2026: Account Usage New CORTEX_AI_GUARDRAILS_USAGE_HISTORY view¶

The ACCOUNT_USAGE schema now includes a new CORTEX_AI_GUARDRAILS_USAGE_HISTORY view that provides visibility into the usage history of Cortex AI Guardrails.

The information in the view includes guardrail scan results, credit and token consumption, and whether any scan was flagged. Each row represents a single guardrail scan for one tool use within an agent request. A request with multiple tool results produces multiple rows, one per tool use scanned. Each row includes the agentic source (Cortex Code, Snowflake Intelligence, or Cortex Agents), granular token and credit breakdowns, and metadata such as the role used.

For more information, see CORTEX_AI_GUARDRAILS_USAGE_HISTORY view.