---
format: "aidr-story-markdown/v1"
id: "d5272da6016d5a4a644e7527becbb934dea5885307576249472e4ae706cce9b8"
canonical_url: "https://aidr.today/d5272da6?lang=en"
title: "Check what your AI agents do before they do it, with Semantic governance policies"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-20T22:59:43.000Z"
category: "Tools"
topics: ["google","safety","devtools"]
source_urls: ["https://developers.googleblog.com/check-what-your-ai-agents-do-before-they-do-it-with-semantic-governance-policies/"]
summary: "Semantic governance policies allow developers to govern AI agents by evaluating proposed tool calls inline before execution via Agent Gateway. The policy engine checks actions against user intent and plain-language rules to prevent prompt injection attacks and unauthorized data sharing. Developers can attach natural-language constraints to agents and monitor verdicts through Cloud Logging."
---

# Check what your AI agents do before they do it, with Semantic governance policies

> [Open the canonical story](<https://aidr.today/d5272da6?lang=en>)

**Published:** 2026-11-20T22:59:43.000Z
**Category:** Tools
**Topics:** google, safety, devtools

## Summary

Semantic governance policies allow developers to govern AI agents by evaluating proposed tool calls inline before execution via Agent Gateway\. The policy engine checks actions against user intent and plain\-language rules to prevent prompt injection attacks and unauthorized data sharing\. Developers can attach natural\-language constraints to agents and monitor verdicts through Cloud Logging\.

## Sources

- [Story source](<https://developers.googleblog.com/check-what-your-ai-agents-do-before-they-do-it-with-semantic-governance-policies/>)

