Gemma 4 production stack: Model Armor, ADK Agents, Tracing

Google Cloud Tech · Intermediate ·🤖 AI Agents & Automation ·2w ago
GCP credit → https://goo.gle/handson-ep8-lab1 Lab → https://goo.gle/guardians Gemma 4 is deployed. Now we secure it, build an agent on it, and make it observable. 🛡️ Model Armor — scans every prompt and response for jailbreaks, PII, and harmful content via a Load Balancer Service Extension. 🤖 ADK Agent — built with Agent Development Kit, powered by vLLM, deployed to Cloud Run via CI/CD. 📊 Prometheus Sidecar — scrapes vLLM metrics: token throughput, GPU utilization, latency. 🔍 Cloud Trace — OpenTelemetry tracing through the agent, end to end. Security. Agents. Observability. One stack. 👇 Chapters: 0:00 - Intro 8:25 - Erecting the shield of SecOps: Setup Model Armor 38:37 - Raising the watchtower: Agent pipeline 57:17 - The palantir of performance: Metrics and tracing 1:07:46 - The boss fight 1:12:30 - Wrap up More resources: Agent Development Kit (ADK) docs → https://goo.gle/4uflScr Model Armor documentation → https://goo.gle/4mz57Ga Cloud Trace documentation → https://goo.gle/4euYyCB Watch more Hands on AI → https://www.youtube.com/watch?v=qCBreTfjFHQ&list=PLIivdWyY5sqKnJOvP89yF8t9mWuzMTcbM 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #Gemma4 #ModelArmor Speakers: Ayo Adedeji, Annie Wang Products Mentioned: Cloud Run, Cloud Build, Model Armor, Agent Development Kit, Cloud Trace, Gemma 4
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Beyond the Prompt: Building Your First Production-Ready Agent with p-agent and MCP
Learn to build a production-ready agent using p-agent and MCP, enabling autonomous systems that interact with the real world
Medium · Python
Your Phone’s Secret AI Sensors
Discover the secret AI sensors in your phone and how they collect data without consent, sparking a growing privacy debate
Dev.to AI
How 10 Agencies Are Running Claude for Their Clients Without the Billing Nightmare
Learn how 10 agencies are managing Claude for their clients without billing issues, using strategies like automated workflows and cost-splitting methods
Dev.to AI
You Don’t Need More Meetings You Need Better Systems Powered by AI
Learn how AI-powered systems can reduce meetings by streamlining workflows and improving team alignment
Dev.to AI

Chapters (6)

Intro
8:25 Erecting the shield of SecOps: Setup Model Armor
38:37 Raising the watchtower: Agent pipeline
57:17 The palantir of performance: Metrics and tracing
1:07:46 The boss fight
1:12:30 Wrap up
Up next
This AI agent writes VIRAL posts
Diandra Escobar
Watch →