Semantic governance policies
Semantic governance policies are business rules written in plain English. An LLM-based policy engine checks every tool call a model proposes against those rules and against what the user actually asked. Watch a refund pass, a refund fail, and an injected refund get caught.
Checking your access…
This is a Pro lesson
Sign in to continue. Pro members get every animated lesson, its code and its quiz, across ADK, Agent Platform, Agent QA and CX Agent Studio.
You're signed in, but this lesson is part of Pro
Get every Pro lesson, its code and its quiz for ₹999, once. Lifetime access, including lessons added later.
Unlocking your lesson…
If this doesn't change in a moment, reload the page.
In this module: Agent Gateway and policies
- Agent Gateway overview One governed path for all agent traffic. Pro
- Set up Agent Gateway Managed gateway, VPC connectivity and routing. Pro
- Route Agent Runtime traffic through the gateway Putting deployed agents behind policy. Pro
- Delegate authorization Letting an external system decide who gets in. Pro
- Extensible policies Service extensions on the gateway. Pro
- Unified Access Policies IAM policies and CEL conditions for agents. Pro
- Semantic governance policies Rules about what agents may say and do. Pro
- Token management policies Controlling token spend. Pro
- Model Armor on the gateway Screening prompts and responses in transit. Pro
- Dry runs and security findings Testing policies before enforcing them. Pro
- Agent anomaly detection Spotting agents that behave unusually. Pro