Gemini Enterprise Agent Platform: Semantic Governance Policies Preview
Gemini Enterprise Agent Platform now offers Semantic Governance Policies (SGP) in Public Preview, providing an intelligent security and compliance layer for AI agents. SGP evaluates tool calls against user intent and business rules at runtime, helping prevent unauthorized actions and data exfiltration. This feature is available for testing in Log Explorer before enforcement, aiding engineers and architects in securing AI agent deployments.
Features (1) ›
- Gemini Enterprise Agent Platform Semantic Governance Policies available in Public Preview
Semantic Governance Policies available in Public Preview Semantic Governance Policies (SGP) and the SGP engine are now available in Preview . SGP provides an intelligent security and compliance layer that evaluates an AI agent's proposed tool calls against user intent and organizational business rules at runtime. Key capabilities include: Natural Language Constraints (NLC): Author declarative business rules and security guardrails in plain English without needing to write code or redeploy agent applications. Layered Intent Gating: Intercepts agent tool calls at runtime to verify alignment with
https://docs.cloud.google.com/release-notes#June_29_2026