proomt

Search

Search posts, papers, and topics

All posts

Google DevelopersEric Dong, Shubham Saboo10 min readintermediate

Build zero-trust AI agents that judge intent, not just syntax

Read on googleblog.com

Summary

Google's Gemini Enterprise Agent Platform adds three managed runtime controls—Model Armor, Semantic Governance Policies, and Agent Anomaly Detection—to protect LLM agents from prompt injection, social‑engineering refunds, and multi‑turn abuse, moving enforcement out of agent code.

  • Model Armor screens inbound prompts and outbound responses at the gateway, blocking jailbreaks and redacting sensitive data before the model runs.
  • Semantic Governance Policies let business owners write natural‑language constraints that evaluate each tool call against intent, denying disallowed refunds without code changes.
  • Agent Anomaly Detection watches session telemetry across turns, flagging cumulative abuse that single‑turn checks miss.
  • All three controls are enforced by the platform’s Agent Gateway, separating governance ownership from the agent developer.

Teams deploying LLM‑powered agents need runtime safeguards that understand intent and behavior, not just static syntax checks, to prevent sophisticated attacks.

7/10
llmsecuritycloudpythonai

Related reading

  1. Agent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform

    Google’s Gemini Enterprise Agent Platform now offers a private‑preview Agent Anomaly Detection service that asynchronously analyzes agents’ OpenTelemetry traces and logs to flag risky behavior (e.g., tool misuse, privilege abuse) without adding latency, surfacing findings in Security Command Center and via an API for automated mitigation.

    Google Developersgoogleblog.com4 min

  2. Changing the game: How Google uses agentic AI to secure hundreds of millions of lines of code

    Google’s AI & Infrastructure team built an agentic pipeline (Mantis) that runs pre‑submit AI‑driven scans on every code check‑in, validates findings with a fast triage agent (AST + call‑graph analysis) achieving >92% precision in <1 min, then auto‑generates fixes via a bug‑fix agent. Localized threat models and a two‑step scan cut false‑positives to ~3% and prevent hundreds of vulnerabilities eac…

    Google Cloud Bloggoogle.com4 min

  3. The DevFest Community Workshop Experience: Building Real Agents Together

    Google’s DevFest Community Workshop introduced a “Workbench” format that emphasizes architectural mental models over copy‑paste code, guiding engineers to build long‑running, self‑evolving multi‑agent systems with the Agent Development Kit and Gemini Enterprise platforms. Attendees learned state‑separation, workflow pausing, and self‑patching pipelines, and the series will continue in five more c…

    Google Cloud Bloggoogle.com2 min

  4. Cloud CISO Perspectives: How Google monitors AI threats and advances AI defenses

    Google’s Threat Intelligence team outlines three AI‑driven shifts—software build changes, expanded attack surface, and enhanced threat capabilities—then describes their multi‑model, graph‑based defense stack (AI Threat Tracker, in‑editor “spellcheck”, Wiz Security Graph, Gemini‑powered AI Threat Defense) and concrete threat examples like supply‑chain poisoning, LLMJacking, and AI‑orchestrated cre…

    Google Cloud Bloggoogle.com11 min

  6. Gemini 3.8 Live models now available on AI Gateway

    Vercel AI Gateway now offers Google’s Gemini 3.8 Live and Live Extended Thinking models through its realtime WebSocket API, enabling real‑time spoken interactions with audio output and parallel reasoning. The post includes a short TypeScript example for token acquisition, WebSocket setup, and handling of realtime events.

    Vercelvercel.com1 minrelease