Annie is taking over the Google Cloud Tech channel for the month of August! Subscribe so you don't miss any of Annie's newest content. Annie will be highlighting her path to Google, her hobbies outside of work, and, of course, awesome tips and neat tricks for cloud developers.

The Tokenomics Foundation → https://goo.gle/4w4qnHd The FinOps Foundation → https://goo.gle/3U3IeR0 The Five-Layer Cake of Tokenomics: How Pinterest Thinks About AI Efficiency → https://goo.gle/44YEFy2 Are your AI budgets exploding? In this episode of The Agent Factory, host Luke Schlangen sits down with J.R. Storment, the newly appointed head of the Tokenomics Foundation under the Linux Foundation. Together, they discuss the industry's rapid shift from the era of tokenmaxxing to the great token panic, exploring how enterprises can scale AI agents without blowing through their revenue. J.R. introduces the emerging discipline of Tokenomics—defined simply as energy to intelligence to value—and maps it across three critical pillars: 1. Production: Data centers, edge devices (such as local Mac Minis or phones), and procured tokens. 2. Consumption: Programmatic model routing, caching, and prompt architecture. 3. Value: Monetization, hybrid credit systems, and the shift from seat-based to usage-based pricing models. They also cover Adobe's Big T framework for token efficiency, Pinterest's five-layer cake of consumption, and how hardware memory bottlenecks are ending the era of subsidized AI. Plus, don't miss J.R.'s predictions in our Rapid Fire Round on the future of algorithmic resource optimization! Chapters: 0:00 - Intro 1:15 - Meet J.R. Storment & The Linux Foundation 2:18 - The parable of the blind men and the elephant 5:34 - From token maxing to the great token panic 10:29 - The nonlinear growth of global tokens 12:36 - The explosion of context windows & agentic loops 14:02 - Global token projections (Goldman Sachs data) 15:38 - What is a token? The 4 core functions 19:59 - The Broad AI spend landscape & KV cache 28:09 - Defining tokenomics: Energy to intelligence to value 29:58 - FinOps vs. tokenomics 31:19 - Production: Data centers, edge, & local tokens 35:38 - Consumption: Pinterest's five-layer cake & Adobe's levers (Big T) 40:40 - Value: The Shift from Seats to Usage-Based Pricing 45:19 - The birth of the Tokenomics Foundation & Tokenomicon 52:46 - Rapid fire round: Predicting the future of token efficiency 56:43 - Outro & advice for engineers More resources: * FOCUS Open Source Spec for Cloud Billing → https://goo.gle/4vXdrmo * Token Economics: The Atomic Unit of AI Value → https://goo.gle/4xbsjOS * FinOps Foundation Framework → https://goo.gle/3TOdovE Watch more The Agent Factory → https://www.youtube.com/playlist?list=PLIivdWyY5sqLXR1eSkiM5bE6pFlXC-OSs 🔔 Subscribe to Google Cloud Tech → https://www.youtube.com/@googlecloudtech #AIAgents #Tokenomics #CloudFinOps #GenerativeAI #GoogleCloudTech #TheAgentFactory Speakers: J.R. Storment, Luke Schlangen Products Mentioned: Google Kubernetes Engine, Gemini, Antigravity

Experience these in action → https://goo.gle/4fLO5lj Explore the differences and synergy between Model Context Protocol (MCP) and Skills when building on and with AI. In this conversational breakdown, we explain how MCP standardizes how large language models connect to programmatic APIs and file systems, and how Skills use progressive disclosure to load instructions only when needed. Watch more AI Builder Essentials → https://goo.gle/AI-Building-101 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Greg Baugues, Tilde Thurium Products Mentioned: Gemini

Gemini Enterprise Agent Platform → https://goo.gle/4x2pKi8 Anthropic's Claude on Google Cloud models → https://goo.gle/4fAqu8x Are AI coding agents killing developer craft, or are AI coding agents being used incorrectly? In this discussion, YK and Lydia break down why using Claude Code requires shifting your mindset from writing code to mastering code review, testing, and production safety. Watch along and learn how to leverage draft PRs, git hooks, and verification layers so you never ship unvetted AI-generated code. Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speakers: YK Sugi, Lydia Hallie Products Mentioned: Gemini Agent Platform, Claude

Gemini Enterprise Agent Platform → https://goo.gle/4x2pKi8 Anthropic's Claude on Google Cloud models → https://goo.gle/4fAqu8x Generating code with AI is easy, but keeping your repo lean requires intentional design and strict developer oversight. In this video, Smitha, YK, and Lydia discuss practical tips for evaluating AI output, setting up agent environments, and mastering high level software architecture. Upgrade your dev workflow to maintain high code standards while building faster with AI agents. Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speakers: Smitha Kolan, YK Sugi, Lydia Hallie Products Mentioned: Gemini Agent Platform, Claude

Gemini Enterprise Agent Platform → https://goo.gle/4x2pKi8 Anthropic's Claude on Google Cloud models → https://goo.gle/4fAqu8x Gemini Enterprise Agent Platform remote MCP server → https://goo.gle/4yMiEzV Set up Claude Code on Google Cloud Console with Gemini Agent Platform (formerly known as Vertex AI) to unlock powerful AI-driven coding workflows.In this demo, YK builds a 3D web application using HTML, JavaScript, Three.js, Rapier physics, and Vite. Watch along and learn best practices for AI agent prompting, project folder structure, Git CLI automation, and continuous verification. Chapters: 0:00 - Intro 0:03 - Setting up Claude code on Google Cloud 1:29 - Introducing YK Sugi 2:43 - Building a slingshot game 3:36 - Tip 1: Talk to your agent with your voice 3:58 - Tip 2: Have a projects folder with most of your projects 5:10 - Tip 3: Ask broader questions first 5:25 - Tip 4: Go back and forth with the agent to refine your idea 6:15 - Tip 5: Learn to use Git and GitHub CLI well 8:31 - Tip 6: Learn to verify the output 8:50 - Tip 7: Automate testing as much as possible 9:17 - Wrap up Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speakers: Smitha Kolan, YK Sugi, Lydia Hallie Products Mentioned: Gemini Agent Platform, Claude

Can AI build a complete multi-level game from a visual design spec? Watch along as Lydia Hallie, DevRel at Anthropic, uses Claude Design and Claude Code on Gemini Agent Platform (formerly Vertex AI) to turn HTML wireframes into a fully functional game. Discover how dynamic workflows and parallel sub-agents automate complex coding tasks, build game logic, and run deterministic pipelines. And finally, observe how Fable 5 takes a visual plan and builds a multi-level game complete with haptics, UI, and audio. Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speaker: Lydia Hallie Products Mentioned: Gemini Agent Platform, Claude

Get started with AlloyDB → https://goo.gle/4d3cuSe In this demo, Alan Li (Principal Engineer, Google) showcases the power of AlloyDB hybrid search. *Key highlights include:* * The AlloyDB hybrid search UDF that uses RRF (Reciprocal Rank Fusion) out of the box to rank joint results from both vector and full text search. * The AlloyDB Elasticsearch FDW that enables executing full-text searches against specialized external data stores (e.g., Elasticsearch). * Transform your cloud and AI journey by bringing the best of Google Research to the best of PostgreSQL. Watch more Understanding AlloyDB → https://goo.gle/UnderstandingAlloyDB 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speaker: Alan Li Products Mentioned: AlloyDB for PostgreSQL

Antigravity → https://goo.gle/4biai9b Codelab on Getting started with Antigravity → https://goo.gle/4hyDMU3 Are we witnessing the end of traditional programming, or just the beginning of a fundamental shift in developer identity? In this episode of the Agent Factory, host Smitha Kolan sits down with Alberta Devor Ver (aka Alberta Tech), an ex-Google engineer who transitioned from building infrastructure to leading tech commentary with nearly 1 million followers. Together, they break down the reality of "vibe coding," what AI agents actually mean for software engineering, and whether the junior engineer role is on the brink of disappearing. Alberta shares her journey from working on Google Maps data infrastructure and YouTube Labs features to building a full time creator career. Watch an unscripted, live demonstration of Google Antigravity as it plans, scrapes, summarizes, and ranks Hacker News discussions in real time with zero manual lines of code written. The duo also discusses the incoming code quality crisis, whether engineers are losing core technical skills, and how technical founders can build an authentic audience without sounding sales-y. Whether you are a developer integrating AI coding tools into your workflow, a technical founder scaling your distribution, or evaluating if learning to code is still worth it, this conversation offers practical strategies and industry perspective. Chapters: 00:00 - Guest intro: Alberta Tech 01:51 - Leaving Google to become a full time creator 02:38 - What is "vibe coding"? 03:27 - How vibe coding "fixed my imposter syndrome" 04:21 - Live demo: Google Antigravity scrapes & ranks HackerNews 09:46 - Is an AI code quality crisis coming? 10:48 - Will AI replace junior engineers? 12:58 - Are we offloading too much zhinking to AI? 14:29 - What will software engineers do in 2 years? 15:31 - Developer sentiment: AI threat vs productivity noost 16:57 - Is it still worth learning to code? 18:18 - How technical founders can build an audience 19:13 - Upleveling technical topics for a broader audience 22:54 - Rapid fire: CS degrees, standups & LeetCode More resources: Developing agents on Google Cloud → https://goo.gle/4bzLqdp Introducing Google Antigravity 2.0 → https://goo.gle/4hztwem Connect with the speakers online: *Smitha* (Host): * YouTube → https://goo.gle/Smitha-on-YouTube * LinkedIn → https://goo.gle/Smitha-on-LinkedIn * X → https://goo.gle/Smitha-on-X *Alberta Devor / @AlbertaTech:* * YouTube → https://goo.gle/AlbertaTech-on-YouTube * TikTok → https://goo.gle/AlbertaTech-on-TikTok * Instagram → https://goo.gle/AlbertaTech-on-Instagram Watch more of The Agent Factory → https://www.youtube.com/watch?v=qBOvM7SiDa4&list=PLIivdWyY5sqLXR1eSkiM5bE6pFlXC-OSs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Smitha Kolan, Alberta Devor Ver Products Mentioned: Google Maps, YouTube, YouTube Labs, Antigravity

In this video, Mazlum Tosun walks Martin Omander through building and deploying an AI data agent. Watch along as the team takes a BigQuery database (the company's data goldmine) and open it for plain English questions, using Agent Development Kit (ADK) and Model Context Protocol (MCP). *Why do this?* Instead of writing endless custom SQL queries or building static dashboards every time a business stakeholder needs an update, this architecture allows non-technical team members to query data using plain natural language. Business teams get instant answers, and developers get out of the dashboard-maintenance loop. Resource links: * High-level project summary → https://goo.gle/3TbsDPbj * Step-by-step blog post → https://goo.gle/4fu9mj9 * Code for this episode → https://goo.gle/4pB24yJ Watch more Serverless Expeditions → https://goo.gle/ServerlessExpeditions 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #ServerlessExpeditions #GoogleCloud Speakers: Martin Omander, Mazlum Tosun Products Mentioned: BigQuery, Agent Development Kit, Cloud Run

Experience these concepts in action here. → https://goo.gle/4wpbQqC Demystify the foundational concepts of building with AI in this conversational breakdown about tokens, context windows, and Retrieval Augmented Generation (RAG). In this video, we cover ""vibe-coding"" concepts including: how large language models (LLMs) operate using tokens, what a context window is, how RAG helps augment model inference with real-time data, conversation compression, and the economics of ""token maxxing." Watch more AI Builder Essentials → https://goo.gle/AI-Building-101 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Greg Baugues, Tilde Thurium Products Mentioned: Gemini

Ready to build your own AI prototyping sandbox with AI Studio and Google Cloud? Check out this codelab → https://goo.gle/4ylGxOw Building a cool AI prototype over a cup of coffee is easier than ever. But inside a massive enterprise, vibe coding quickly hits a wall of infrastructure, data compliance, and security guardrails. In fact, only 5% of AI prototypes ever make it to production. So how does a billion-user platform like YouTube move fast without breaking things? In the premiere episode of Emergent, Stephanie goes into the engineering trenches with AI leaders to break down YouTube’s Prototyping Stack to show how they ship AI features fast and safely. Learn how to shift your mindset, embrace throw-away code, and build a sandbox that lets your team fail safely at hyper-speed. Chapters: 0:00 — Why 95% of AI apps fail in production 0:37 — The developer risk vs. speed dilemma 2:34 — The invisible friction of vibe coding 4:41 — YouTube's billion user blast radius 6:55 — The blank canvas prototyping trap 7:53 — Inside YouTube's AI prototyping stack 9:18 — Embracing throwaway code 10:19 — Democratizing prototyping at Google scale 11:46 — Becoming an architect of safety Subscribe to Google Cloud Tech for more deep dives into cloud architecture and AI dev workflows → https://goo.gle/GoogleCloudTech #GoogleCloud #GoogleAIStudio #Vibecoding Speakers: Stephanie Wong, Addy Osmani, Benji Bear Products Mentioned: Google AI Studio, Google Cloud

Multi-agent systems are increasingly vulnerable to prompt injections, data leaks, and denial-of-service attacks when their endpoints are left exposed. In this session, developers will learn how to implement a comprehensive defense-in-depth strategy to secure AI agents using Google Cloud’s native security tools. *Join us and learn:* * How to implement Sensitive Data Protection (SDP) to redact PII before it reaches agents. * How to integrate Model Armor to intercept and sanitize user prompts against malicious injections. * Learn the workflow for running live Red Team scenarios to stress-test defenses. * How to manage security guardrails at scale using "Policy as Code" with Terraform. * How to apply defense-in-depth principles to protect multi-agent architecture. * How to ensure consistent security posture across development and production environments. *Resources:* * Codelab: Securing a Multi-Agent System → https://goo.gle/3T9Z2FK * Google Cloud Sensitive Data Protection documentation → https://goo.gle/4h6gu8b * Model Armor overview → https://goo.gle/4hswp0m * Google Cloud AI security best practices → https://goo.gle/4pDltPS Ready to build? Try this in Google Cloud Codelabs here. → https://goo.gle/4vGkaAX This livestream originally aired on July 21, 2026 at 1:00 P.M. PDT / 4:00 P.M. EDT. #ModelArmor #CloudSecurity Speakers: Aron Eidelman, Leonid Yankulin Products Mentioned: Gemini, Model Armor, Cloud Security

Learn more about CodeMender → https://goo.gle/4w9eXCD Learn more about Google AI Threat Defense → https://goo.gle/4fhvkHD Struggling to keep pace with AI-driven software vulnerabilities? Meet Google CodeMender—an autonomous AI code security agent pioneered by Google DeepMind and now available on the Gemini Enterprise Agent Platform. In this deep-dive demo, we show you how CodeMender helps development and security teams "shift left" by finding, verifying, and patching deep software vulnerabilities directly within developers' existing tools like VS Code. Learn how CodeMender automatically generates code verification plans, runs safe proof-of-concept exploits to verify real risks, writes precise remediation patches, and seamlessly integrates with Wiz for risk prioritization and Mandiant for strategic threat intelligence. Watch to see how you can maintain full developer control while securing your codebase at machine speed. Chapters: 0:00 - Introduction: AI powered threats 0:14 - Meet Google CodeMender 0:35 - Developer tool integration (VS Code setup) 0:42 - Scan: Identifying vulnerabilities in Code 0:54 - Exporting & reviewing HTML security reports 0:59 - Verify: Proof-of-concept exploit execution 1:14 - Remediate: Generating patches and code fixes 1:23 - Developer Code review & git diff control 1:32 - Summary: Codemender 1:46 - Outro: Google AI threat defense (CodeMender, Wiz, & Mandiant) *More resources:* * Read the CodeMender announcement → https://goo.gle/4vLILo1 * Google DeepMind original research on CodeMender → https://goo.gle/3RjsCYE 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleCloud #CodeMender #AppSec #AISecurity #DevSecOps #Wiz #Mandiant #GoogleDeepMind #AgentPlatform Speakers: Aron Eidelman Products Mentioned: CodeMender, Wiz, Mandiant

Discover how to deploy Google’s Network Security Integration - in line. This video drives into micro segmentation with Network Security Integration - in band through next generation firewall policies. You will also see a demo using Google Cloud and Check Point Firewalls Chapters: 0:00 - Introduction 0:19 - Challenges 0:46 - Intro Network Security Integration 1:07 - Demo Description 1:26 - Console Demo Check Point 8:27 - Outro Resources: Codelabs → https://goo.gle/4yrKgKs Check Point lab → https://goo.gle/4bMGeTf In-band integration overview → https://goo.gle/4wbqrFU Google Cloud Advanced Networking demo series playlist → https://goo.gle/AdvancedNetworking Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleCloud #NSI #Networking #Networksecurityinsertion #cloudsecurity Speakers: Harika Rama K, Gustavo Coronel Products Mentioned: Network Security Integration

Vibe coding a flawless AI prototype locally is easy. Shifting that experimental code into a production system handling billions of users without crashing your servers? That's where things get complicated. Statistically, 95% of enterprise AI prototypes never make it to production. In our brand-new video, Emergent, Google Cloud’s Stephanie Wong goes inside Google's own engineering trenches. She’ll pull back the curtain on the frameworks and architecture philosophies for the 5% of AI applications that ship. The video premiere drops on *Tuesday, July 21, 2026.* 🔔 Subscribe and turn on notifications for the premiere → https://goo.gle/GoogleCloudTech #AIEngineering #GoogleCloud #Vibecoding Speaker: Stephanie Wong Products Mentioned: Google AI Studio, Google Cloud

In this video, Kaz Sato shows Martin Omander how to add smart semantic search to an app using Agent Retrieval (previously known as Vector Search 2.0). If a user searches your store for "something warm to wear in the snow" but your database only contains "heavy winter jacket," traditional keyword search fails and returns zero results. This will cost you users and revenue. Unlike traditional keyword search which breaks on simple synonyms and exact string matches, Agent Retrieval maps the actual meaning and intent behind a query, handling synonyms automatically with zero manual embedding pipeline overhead. 🛠️ *What we cover:* * The problem: Why keyword search isn't enough for modern user expectations. * Agent retrieval: How to generate vector embeddings automatically. * Hybrid search: How to combine keyword and vector search for the best of both worlds. 🔗 *Code & resources:* * Kaz’s blog post with more details and code → https://goo.gle/4wAXyCH * Kaz’s notebook that lets you play with semantic search → https://goo.gle/3TyXBAE * Agent Retrieval documentation → https://goo.gle/4vuaGsr Chapters: 0:00 Intro 0:45 Why use Semantic search? 2:12 Agent Retrieval can help you 2:28 Code walkthrough 4:14 Demo: Results from Agent Retrieval 4:50 Takeaways Watch more Serverless Expeditions → https://goo.gle/ServerlessExpeditions 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #ServerlessExpeditions #GoogleCloud Speakers: Martin Omander, Kaz Sato Products Mentioned: Agent Retrieval, Vector Search 2.0

Experience an agentic harness in action → https://goo.gle/4f3PFjs Demystify the concept of an Agentic Harness and learn how they power modern AI systems. In this conversational breakdown, we explore the definition of agents and harnesses, and how both differ from the core LLM and user interfaces. Watch more AI Builder Essentials → https://goo.gle/AI-Building-101 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Greg Baugues, Tilde Thurium Products Mentioned: Antigravity

White-paper on context engineering → https://goo.gle/3QiKYbT More info on context engineering → https://goo.gle/43fII8c Context Engineering: Why writing bigger prompts won't fix your AI, and what to do instead. In this video, Smitha Kolan explains what context engineering is, how it's different from prompt engineering, and gives you a practical step-by-step framework to build smarter, more reliable AI agents. Models keep getting larger context windows, but longer context isn't always better. When the windows is stuffed with everything, accuracy drops and errors sneak in. Context engineering is the discipline of curating the smallest set of high-signal information the model needs at each step: the right instructions, the right tools, the right facts, and nothing more. In this video you'll learn: * 📌 The 7 components of a well engineered context stack. * ⚠️ The 4 failure modes that break AI agents. * 🛠️ The 4 steps of context engineering. Chapters: 0:00 - Bigger prompts don't fix bad AI 0:47 - What is context engineering? 1:39 - Why context size isn't everything 2:18 - Four failure modes: Poisoning, distraction, confusion, clash 2:58 - Context engineering vs prompt engineering 4:16 - The seven components of a context stack 5:02 - Building LogLook: A realistic agent example 7:00 - The 4 steps of context engineering 7:08 - Step 1: Write 7:50 - Step 2: Select 8:34 - Step 3: Compress 9:14 - Step 4: Isolate 9:50 - Curate, don't dump More resources: MCP Explained → https://goo.gle/3QY4Hhw MCP vs API → https://goo.gle/4ffLPCF Watch more Modern AI Agents: From Theory to Production → https://goo.gle/Learn-with-Smitha 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #ContextEngineering #PromptEngineering #AIAgents #GoogleCloud #Gemini #ArtificialIntelligence #MachineLearning Speaker: Smitha Kolan Products Mentioned: AI Infrastructure

KodeKloud AI tutor → https://goo.gle/44Zrg8C Welcome back to The Agent Factory! In this episode, host Luke Schlangen sits down with Mumshad Mannambeth, the founder of KodeKloud, to explore the future of DevOps, cloud upskilling, and building production-ready AI agents. Mumshad shares an exclusive, behind-the-scenes look at how KodeKloud built their cutting-edge AI Tutor—a hands-on, AI-assisted learning platform that has doubled student retention! We dive deep into the multi-agent architecture under the hood, showing how they orchestrate five specialized agents using LangGraph and cost-effective Gemini Flash models on Google Cloud. Mumshad also walks us through their implementation of Model Armor on Cloud Run to secure LLM calls against prompt injections and malicious inputs, and how they synchronize AI-generated voice with dynamic React code to generate video lessons on the fly. We also tackle the shifting landscape of tech interviews, why foundational knowledge in Kubernetes and Linux is more critical than ever, and how to avoid developer burnout in the age of AI. Stick around for a rapid-fire round where Mumshad shares his thoughts on whether certifications are overrated, if Python should be your first language, and how to navigate the overwhelming CNCF landscape. Chapters: 0:00 - Intro 0:44 - Do we still need Kubernetes? 1:32 - CKA vs CKAD: Admin vs Developer Kubernetes certs 3:35 - Luke's personal certification journey 4:22 - Running Large Language Models (LLMs) on Kubernetes 5:10 - Do we need humans in DevOps if AI can code? 7:27 - The future of coding interviews & system design 11:25 - The AI productivity paradox: Why are we working more? 12:26 - Navigating the massive CNCF landscape 14:53 - How to learn effectively in the AI era 17:05 - Demystifying KodeKloud's AI Tutor 18:31 - Hands-on Demo: Kubernetes Services Lab 24:07 - Facing the Kubernetes Quiz & Live Terminal 30:31 - Interactive debugging with KodeKloud's Live Assist 35:06 - Sneak peek behind the curtain: AI Tutor under the hood 37:03 - Hosting & scaling 30k virtual labs on Google Cloud 39:06 - How the AI assistant doubled student retention 42:52 - Multi-Agent orchestration with LangGraph 46:14 - Syncing 11 Labs audio with custom React UI 48:11 - Leveraging cost-effective Gemini Flash models 51:25 - Personalization and student memory 53:17 - Google Cloud Run deployment & architecture 54:15 - Protecting LLMs from prompt injection with Model Armor 55:55 - Combatting crypto miners in free sandboxes 58:23 - Rapid Fire: Kubernetes, certifications, and developer burnout 1:03:05 - Mumshad's advice on career transitions & lifelong learning 1:04:32 - Outro More resources: How to deploy an AI agent to Cloud Run (step by step) → https://goo.gle/4haPa8w Watch more of The Agent Factory → https://www.youtube.com/playlist?list=PLIivdWyY5sqLXR1eSkiM5bE6pFlXC-OSs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DevOps #Kubernetes #AIAgents #GoogleCloud #ModelContextProtocol #GenerativeAI #KodeKloud #TheAgentFactory #LangGraph Speakers: Luke Schlangen, Mumshad Mannambeth Products Mentioned: Google Cloud Run, Google Kubernetes Engine, Google Cloud Build, Google Artifact Registry, Google Secret Manager, Google Model Armor, Gemini Flash, LangGraph, 11 Labs, Prometheus, Grafana, MongoDB, Docker, Podman

*Download Google Antigravity here.* → https://goo.gle/4fdw536 Are AI coding agents writing your features, or just writing your bugs? A common complaint about AI development tools is that while they generate code quickly, they also create a massive amount of technical debt. Developers tend to over-rely on AI to write code, but don't use it enough to maintain, review, or test it. In this video, YK Sugi walks through how to apply agentic workflows to an entire Software Development Lifecycle (SDLC) using *Google Antigravity*. Whether orchestrating multiple local agents in parallel through the Antigravity 2.0 command center, managing background subagents from the terminal-first Antigravity CLI, or prototyping custom behavior with the SDK, this platform is designed to help you build in the agent-first era. Using real open source examples—like customizing a GitHub profile card—YK demonstrates how to speed up workflows and let agents do the heavy lifting, without losing control of your codebase. *What we cover:* * *Step 1:* Identifying and summarizing complex GitHub issues autonomously. * *Step 2:* Collaborating with coding agents on system design and architecture. * *Step 3:* Live implementation and flexible feature customization. * *Step 4:* Deep, line-by-line PR reviews and automated testing. Chapters: 00:00 - The problem: More AI code = more tech debt 00:44 - The agent-powered SDLC explained 01:23 - Step 1: Identifying & understanding issues 04:32 - Step 2: Designing the solution 06:53 - Step 3: Implementation & live demo 16:03 - Step 4: PR reviews & testing with Google Antigravity 🔗 *Resources Mentioned:* * Google Antigravity: Experience liftoff with the next-gen agent platform (IDE, CLI, and SDK). Download it here. → https://goo.gle/4fdw536 Speaker: YK Sugi Products Mentioned: Antigravity

Try it out here. → https://goo.gle/44uwXLz The BigQuery Agent Analytics Block, now available in the Looker Marketplace, provides an analytics solution designed to give you immediate visibility into your AI agent's behavior and performance. 🔭 Discover more tools for Looker data teams → https://www.youtube.com/playlist?list=PLIivdWyY5sqIQl0c0Cpe2Z7qiQhTqNpsu 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #AIAgents #ADK #LangChain #AgentAnalytics #Observability #BigQuery #Looker #Agents Speaker: Chrissie Goodrich Products Mentioned: BigQuery, Looker

Watch along as Jason and Sujay discuss their thoughts on the latest developments in AI agents. Speakers: Jason Lopatecki, Sujay Solomon Products Mentioned: Gemini

Gemini Enterprise Agent Platform → https://goo.gle/4gTwpX6 Agent Observability → https://goo.gle/44zI8Tz Agent Registry → https://goo.gle/4bwecv9 Discover how European retail giant MediaMarktSaturn Technology scales developer velocity using Google Cloud Platform. In this interview, Cédric Yao from Google Cloud and Ervis Duraj, Principal Software Engineer, discuss moving beyond shifting left to "shifting down"—embedding governance and self-service into the platform. Hear how MediaMarktSaturn Technology used Gemini CLI and Gemini Cloud Assist to build 130+ agentic skills, share Terraform modules, cut developer onboarding from weeks to minutes, and use AI-driven proactive alerting for faster DevOps troubleshooting. Watch more How orgs are using Google Cloud → https://goo.gle/google-cloud-use-cases 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Cédric Yao, Ervis Duraj Products Mentioned: Gemini

Gemini Enterprise Agent Platform → https://goo.gle/4gTwpX6 Agent Observability → https://goo.gle/44zI8Tz Agent Registry → https://goo.gle/4bwecv9 Discover how Home Depot slashed their incident response times from 20 minutes to under 2 minutes using AIOps on Google Cloud. In this interview, Google Cloud Product Manager Allison Park sits down with Ashish and Chuma from Home Depot’s reliability engineering team. Learn how they use Google Cloud Managed Service for Prometheus (GMP) and OpenTelemetry to establish consistent data labeling and high-cardinality log correlation. See how Gemini models act as an SRE "pair programmer"—providing deep context alerting, root-cause analysis (RCA), and automated troubleshooting. Watch more How orgs are using Google Cloud → https://goo.gle/google-cloud-use-cases 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Allison Park, Ashish Kumar, Chuma Chuma-obi Products Mentioned: Google Cloud, OpenTelemetry, Google Cloud Managed Service for Prometheus, Gemini

Gemini Enterprise Agent Platform → https://goo.gle/4gTwpX6 Agent Observability → https://goo.gle/44zI8Tz Agent Registry → https://goo.gle/4bwecv9 Discover how Palo Alto Networks achieves 5-9s reliability and slashes MTTD/MTTR using Google Cloud Platform. In this interview, Cédric Yao from Google Cloud and Karthik Ravi Prakash, Site Reliability Engineering, discuss building an AIOps framework powered by BigQuery to correlate data and detect infrastructure anomalies proactively. Learn how they leverage Gemini Cloud Assist and the Gemini Enterprise Agent Platform to monitor Kubernetes clusters, run deep investigations, and automate remediation. Listen as Palo Alto Networks shifts from reactive troubleshooting to proactive incident management. Watch more How orgs are using Google Cloud → https://goo.gle/google-cloud-use-cases 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Cédric Yao, Karthik Ravi Prakash Products Mentioned: Gemini, BigQuery, Google Kubernetes Engine

Gemini Enterprise Agent Platform → https://goo.gle/4gTwpX6 Agent Observability → https://goo.gle/44zI8Tz Agent Registry → https://goo.gle/4bwecv9 Why do so many AI agents fail when moving from sandbox to production? Arize AI CEO Jason Lopatecki explains why continuous evaluation and observability act as the essential scaffolding for enterprise automation. Discover how agent harnesses have evolved to solve complex coding problems and why infinite real-world inputs require continuous production monitoring rather than traditional pre-deployment testing. Listen along to learn about the upcoming wave of agent swarm governance, open telemetry standards for agent tracing, and why open source agent frameworks like OpenClaw are exploding. Watch more How orgs are using Google Cloud → https://goo.gle/google-cloud-use-cases 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Jason Lopatecki, Sujay Solomon Products Mentioned: Gemini

Application Management → https://goo.gle/4vO5ccR Gemini Enterprise Agent Platform → https://goo.gle/4gTwpX6 Agent Observability → https://goo.gle/44zI8Tz Agent Registry → https://goo.gle/4bwecv9 Discover how global banking giant BBVA scales its platform architecture to manage thousands of Google Cloud projects. In this interview, Product Marketing Manager Allison Park and Gerardo Mongelli from BBVA's architectural team discuss moving from manual operations to Infrastructure as Code (IaC) with Terraform pipelines. Learn how they use GCP Cloud Hub and App Hub to aggregate resource data into unified application-level views for monitoring, alerting, and cost optimization. Plus, see how they plan to introduce an agentic AI layer for automated notifications. Watch more How orgs are using Google Cloud → https://goo.gle/google-cloud-use-cases 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Allison Park, Gerardo Mongelli de Borja Products Mentioned: Terraform, Google Cloud

Gemini Enterprise Agent Platform → https://goo.gle/4gTwpX6 Agent Observability → https://goo.gle/44zI8Tz Agent Registry → https://goo.gle/4bwecv9 Building AI agents is easy, but running them successfully in production is hard. Discover how PayPal launched an autonomous SRE agent intern ecosystem using Google Cloud's ADK and Gemini Enterprise. Mir from PayPal explains how they automated incident response while managing hallucination and model evaluation out of the box. Watch to see how they utilize supervisor, RCA, and change analyst agents, hook them into an MCP server for history data, and implement essential safety guardrails like allowlists, blocklists, and secure containers for mutating production environments. Watch more How orgs are using Google Cloud → https://goo.gle/google-cloud-use-cases 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Afrina M, Mir, Islam Products Mentioned: Gemini Enterprise app, Agent Development Kit

Discover the latest Google Cloud infrastructure innovations powering large scale AI training, standard compute, and edge deployments. Learn how next generation hardware like 7th-gen Ironwood TPUs and ARM-based Google Axion processors optimize performance and cost effectiveness for enterprise workloads. Explore how Google Distributed Cloud brings Gemini, NVIDIA B300 Blackwell systems, and physical AI simulations directly on-premises for maximum data control. Chapters: 0:00 - Intro 0:23 - Ironwood TPU for large scale training 1:10 - Google Axion processors for standard compute 1:47 - NVIDIA GeForce RTX for deploying physical AI on location 3:23 - Google Distributed Cloud for running Gemini and AI agents on-prem 4:40 - Wrap up 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleCloud #NVIDIA Speakers: Cameron Peron, Chelsie Czop, Robert, Brian Kracik Products Mentioned: Google Axion processors, Tensor Processing Units, Nvidia Blackwell, Google Distributed Cloud, Gemini

Run the codelab today. → https://goo.gle/4g2NY6x Agent Development Kit (ADK) docs → https://goo.gle/4esLqMX MCP explained → https://goo.gle/3QVScTB Stop running AI agents locally! Join Smitha Kolan as she demonstrates how to take a Python AI agent, powered by the Agent Development Kit (ADK) and secured by the Model Context Protocol (MCP), and deploy it cleanly onto Google Cloud Run. Watch along as Smitha demystifies Cloud Run's serverless scaling and explains the precise configuration necessary to build enterprise ready tools using AI systems that reliably scale. Chapters: 0:00 - How to build AI agents with MCP 0:52 - How Cloud Run works 2:11 - Project setup and dependencies 3:36 - Environment variables and service account 4:53 - Building the agent with ADK 6:53 - Setting up MCP and Wikipedia Tools 7:34 - Creating researcher and presenter agents 8:48 - Root agent and workflow 9:30 - Deploying to Cloud Run 10:43 - Testing your live agent 11:26 - Next steps and improvements 12:39 - Cleanup and recap More resources: Agent Development Kit (ADK) documentation → https://goo.gle/4dS4l4w Cloud Run documentation → https://goo.gle/4ulsyVH MCP vs API → https://goo.gle/4eQVGzN 🔗 Connect with Smitha online: YouTube → https://goo.gle/Smitha-on-YouTube Linkedin → https://goo.gle/Smitha-on-LinkedIn X → https://goo.gle/Smitha-on-X Watch more Modern AI Agents: From Theory to Production → https://goo.gle/Learn-with-Smitha 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #CloudRun #AIAgents #GoogleCloud #ADK #Gemini #MCP #ModelContextProtocol #Python #Deployment Speaker: Smitha Kolan Products Mentioned: Cloud Run, Agent Development Kit, Vertex AI, Model Context Protocol, Artifact Registry, Cloud Build

Learn to scale "vibe-coded" prototypes into production-ready apps. See how Google AI Studio automates backends with Cloud SQL and Firestore for real-time data. In this video, the team bridges the "day 2" gap by showing developers how to transition their static prototypes into persistent, enterprise-grade architectures. Learn how to leverage Google AI Studio to autonomously configure database schemas, manage connection strings, and eliminate backend boilerplate, allowing developers to focus on core application logic. The team dives into the technical nuances of choosing between relational (Cloud SQL) and NoSQL (Firestore) databases for AI-generated applications, and demonstrate how to manage user authentication and secure API secrets within an agent-led workflow. Finally, see how to deploy high-performance, full-stack applications at no cost using the Google Cloud Starter Tier. Resources: Get started with Google AI Studio → https://goo.gle/3R9bSTQ What is vibe coding? → https://goo.gle/3RlRoaJ Full-stack vibe coding guide → https://goo.gle/4bxxyA1 Cloud SQL for PostgreSQL documentation → https://goo.gle/4aHP1pa Firestore overview → https://goo.gle/3SPMvXU 🚀 *Try this in the Google Cloud Console:* * Build your first AI-powered app today with no billing required → https://goo.gle/3R9bSTQ This livestream originally aired on July 7, 2026 at 9:00 A.M. PDT / 12:00 P.M. EDT. #GoogleCloud #AIStudio #Firestore #CloudSQL #VibeCoding Speakers: Tilde Thurium, Billy Jacobson Products Mentioned: Google AI Studio, CloudSQL, Firestore

When Sami's app Playback IQ hit the field, it was crippled—90 agonizing seconds of lag stopped the game before it even started. When your AI agent's code feels like a black box, how do you find the bottleneck? This week at the AI Agent Clinic, Luis and Sami cut through the defensive chaos. Watch as Luis attacks from the left with OpenTelemetry to map out the execution spans, while Sami implements parallel processing through the middle to turn 90 seconds into 20. What a match, ladies and gentlemen! Don't miss episode two of the AI Agent Clinic on the Google Cloud Tech channel. #AIAgents #GoogleCloud #Football #Soccer #OpenTelemetry #Developer #Debugging #Latency #Coding #GeminiEnterprise #AgentPlatform Speaker: Luis Sala, Sami Maghnaoui Products Mentioned: Gemini Enterprise Agent Platform, OpenTelemetry, Antigravity IDE

Fable 5 on Google Cloud → https://goo.gle/4wlhp8L Cloud Fable 5 blog → https://goo.gle/4eYyBtP Claude Code on Google Vertex AI → https://goo.gle/4v4gTuP Are you still writing your software architecture line by line, or are you letting autonomous agents do the heavy lifting? In this episode of The Agent Factory, we explore the radical shift toward intent-driven development, where your job is to tell the AI what to build rather than how to build it. Host Smitha Kolan sits down with Lydia Hallie from Anthropic and YK Sugi, the creator of CS Dojo and author of the viral Claude Code Tips repository. Together, they showcase two groundbreaking live demos. First, you'll see how to spin up Claude Code on Google Cloud access massive enterprise scale via the Gemini Enterprise Agent Platform. Then, YK demonstrates building a complete 3D physics slingshot game. Lydia pushes the envelope even further by using Claude Design and the brand-new Dynamic Workflows feature powered by the Fable 5 model to spawn parallel engineering subagents that generate modular UI, audio components, and haptics in real time. Chapters: 0:00 - Introduction to Claude Code & The Guests 01:01 - The Feature Developers Are Sleeping On: Auto Mode 01:11 - The Story Behind YK Sugi's Viral Claude Code Repository 02:50 - Shifting to Intent-Driven Development 03:37 - Why You Should Prompt Using Your Voice Instead of Typing 05:24 - Enterprise Scale: Gemini Enterprise Agent Platform 06:01 - Walkthrough: Setting up Claude Code on Google Cloud 07:35 - Demo: Building a 3D Physics Game via Voice Prompts 17:08 - Automating Code Review with Draft PRs via CLI 19:36 - Demo: Rebuilding UI Layouts Using Claude Design 22:27 - Running the Built-In Vertex AI Setup Wizard 23:39 - Deep Dive: Solving Permission Fatigue in Auto Mode 26:12 - Spawning Parallel Coding Subagents with Dynamic Workflows 31:50 - How AI Shifts the Software Engineer's Role to Product Manager 37:40 - Craft Control vs. Technical Debt: The Hacker News Debate 39:49 - Shifting Mindsets: 90% Coding to 90% Code Reviewing 41:20 - How YK Used Claude Code to Save $10,000 on Real Estate 43:15 - Building Cowork for Desktop and Non-Technical Tasks 44:21 - Rapid Fire Round: The Future of Programming Languages More resources: Build faster with Claude on Google Cloud → https://goo.gle/4wgl5sw Ship Code Faster with Claude Code on Vertex AI → https://goo.gle/4y0SysI YK’s Blog on How to use coding agents → https://goo.gle/4oVHSax YK’s Claude Code Tips → https://goo.gle/4wlx4oK Try Anthropic’s Claude models on Google Cloud → https://goo.gle/4eEtobI 🔗 Connect with the speakers online: *Lydia Hallie* * X → https://goo.gle/Lydia-on-X * LinkedIn → https://goo.gle/Lydia-on-LinkedIn *YK Sugi (CS Dojo)* * X → https://goo.gle/YKSugi-on-X * LinkedIn → https://www.linkedin.com/in/ykdojo/ *Smitha Kolan (Host)* * X → https://goo.gle/Smitha-on-X * LinkedIn → https://goo.gle/Smitha-on-LinkedIn Watch more of The Agent Factory → https://www.youtube.com/watch?v=qBOvM7SiDa4&list=PLIivdWyY5sqLXR1eSkiM5bE6pFlXC-OSs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Smitha Kolan, Lydia Hallie, YK Sugi Products Mentioned: Google Cloud Vertex AI, Gemini Enterprise Agent Platform, Vertex AI Model Garden, Claude Code

A football tournament is underway, and fans demand instant insights! ⚽️ But what happens when your sports analysis app takes over 90 seconds to answer? Join us in the AI Agent Clinic, where Luis Sala and Sami Maghnaoui dive into the code of Playback IQ to fix severe latency before championship-level traffic hits. Built on the Gemini Enterprise Agent Platform and optimized directly inside the Antigravity IDE, the team uses OpenTelemetry to spot sequential bottlenecks. Watch them parallelize the workflow, cut agent execution time by 80%, and keep up with the beautiful game! Speaker: Luis Sala, Sami Maghnaoui Products Mentioned: Gemini Enterprise Agent Platform, OpenTelemetry, Google Cloud Trace, Cloud Run, Antigravity IDE

GitHub repo → https://goo.gle/4y6rlVn Agent Platform observability → https://goo.gle/4eEgzgd Google Antigravity → https://goo.gle/3R5gUki Cloud Run → https://goo.gle/4f3VY6p In this action packed episode of the AI Agent Clinic, developer Sami Maghnaoui brings his sports app, Playback IQ, into the clinic to tackle a major challenge: sluggish generation times during a global football tournament! ⚽️ Watch as AI expert Luis Sala and Sami fire up the Antigravity IDE to diagnose hidden performance bottlenecks. See firsthand how they use Google Cloud’s Gemini Enterprise Agent Platform—the premier unified environment to build, deploy, govern, and optimize enterprise grade AI agents—to completely transform their workflow. Discover how a brilliant mix of OpenTelemetry instrumentation, parallel processing, and a swift Cloud Run deployment took a slow build and turned it into a lightning fast, production ready agent. 🚀 💡 Crucial GenAI Cost Hack: Learn how to track token consumption directly inside your telemetry tools! Watch along and learn how to monitor these metrics to continuously maintain high quality outputs once an app goes live. Do you want to be a guest on The Agent Clinic and have your agent fixed live? Submit your repo to: agent-clinic@google.com. Watch along and learn how to: * Optimize on the agent platform: Use the platform's robust capabilities to slash processing time by 80% by handling SDK outputs and executing voice synthesis in parallel. * Monitor tokens & cut costs: Integrate token consumption tracking to set the stage for lowering costs * Pinpoint latency with Antigravity: Use OpenTelemetry standards inside the Antigravity IDE to send data to Google Cloud Trace, breaking down execution into visual "spans." * Deploy seamlessly: Take your optimized agent straight to production using Cloud Run. Chapters: 00:00 - AI agent latency issues in production (PlaybackIQ case study) 05:30 - Architecture overview: Gemini agent + Vector DB for live sports data 12:15 - Diagnosing high LLM response times under concurrent traffic 18:40 - Configuring OpenTelemetry Tracing for Gemini Enterprise agents 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #AIAgentClinic #GoogleCloud Speakers: Luis Sala, Sami Maghnaoui Products Mentioned: Gemini, Antigravity, OpenTelemetry, Cloud Run, Cloud Trace

MCPs explained → https://goo.gle/4wjeLka Google MCP repo → https://goo.gle/4aeGUA5 Model Context Protocol (MCP) → https://goo.gle/4uQk3D8 MCP vs API: What's the difference and why does it matter for AI developers? In this video, Smitha Kolan breaks down how Model Context Protocol (MCP) works, how it's different from traditional APIs, and why it's becoming the new standard for connecting AI agents to tools, data, and systems. For decades, APIs have been the universal handshake between software systems: clean, predictable, and built for programs talking to programs. But Large Language Models (LLMs) don't just call a single endpoint. They need to chain tools together, interpret unstructured data, and reason about what to do next. APIs weren't designed for that. MCP is. Learn how MCP allows models to autonomously discover and use tools without manual hardcoding or constant prompt engineering, including a real world example of how an AI agent can connect to services like Gmail, Notion, and Jira through MCP without writing custom integration code for each one. Chapters: 0:00 - The big shift in AI: Model Context Protocol 0:45 - APIs vs. MCP: Why APIs aren't enough for LLMs 2:48 - How MCP works: Context vs. hardcoding 4:52 - Real world example: Building an AI agent 6:49 - Under the hood: MCP servers and metadata 8:58 - MCP on top of APIs: The new middleware 10:16 - Challenges with MCP: Security and control 11:29 - The interoperable ecosystem of AI agents More resources: 50+ fully managed MCP servers now available for Google Cloud services → https://goo.gle/4uMMtOx Google Cloud MCP servers overview → https://goo.gle/4g21Vlf Powering the next generation of agents with Google Cloud databases → https://goo.gle/4oa4iV3 🔗 Connect with Smitha online: YouTube → https://goo.gle/Smitha-on-YouTube Linkedin → https://goo.gle/Smitha-on-LinkedIn X → https://goo.gle/Smitha-on-X Watch more Modern AI Agents: From Theory to Production → https://goo.gle/Learn-with-Smitha 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #ModelContextProtocol #GoogleCloud #Gemini #ArtificialIntelligence #AIAgents #MachineLearning #APIs Speaker: Smitha Kolan Products Mentioned: AI Infrastructure, Gemini, Agent Development Kit

GitHub repo → https://goo.gle/oracle-bigquery-mcp FynanceAI: Enterprise Oracle DB & BigQuery ML Real-time Pipeline → https://goo.gle/3QTchcZ Watch this demo and learn how enterprise organizations can move beyond simple conversational chatbots and deploy secure, autonomous agentic AI that safely connects to mission critical systems of record. Using a fictional corporate scenario, this video showcases FynanceAI—a platform powered by Google Cloud's Agent Development Kit (ADK) and the open source Model Context Protocol (MCP) Toolbox—autonomously orchestrating data and executing critical business tasks across Oracle databases, Looker BI, and unstructured vector data stores without sacrificing security or operational control. 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speaker: Rahul Batta Products Mentioned: Agent Development Kit, Model Context Protocol, Looker

Build today → https://goo.gle/4ydeHUS Learn how to build a native Android photography app from scratch in just five minutes using Google AI Studio. This tutorial walks you through the intial prompting and app prototyping with Gemini 3.5 Flash. It also covers how to sideload the app directly to your phone for testing and "vibe code" through bugs, such as fixing photo orientation issues. Finally, we discuss tradeoffs to consider between building PWAs versus native Android apps. Speaker: Tilde Thurium Products Mentioned: Google AI Studio, Gemini

Check out the codelab discussed in this episode here. → https://goo.gle/prai-rs-2 Stop guessing whether AI agents are actually working. Manual vibe checks might be fine for prototyping, but production requires real data. On the next Google Cloud Live stream, the team is showing developers how to move from subjective testing to data driven assessment using Gemini Enterprise Agent Platform Pipelines and Cloud Run functions. Join Vlad Kolesnikov and Leonid Yankulin to learn how to build an automated regression testing pipeline for your distributed multi-agent systems. Watch along and learn: * Data driven assessment: Implement adaptive rubrics and tool use quality metrics to rigorously evaluate AI agents. * Shadow deployments: Safely deploy AI agents to a private tagged revision in Cloud Run. * CI/CD automation: Integrate continuous evaluation into pipelines to ensure code changes never degrade any agent's proven quality. Don't let invisible regressions break your production workflows. This livestream originally aired on June 30, 2026 at 9:00 A.M. PDT / 12:00 P.M. EDT. Speakers: Vlad Kolesnikov, Leonid Yankulin Products Mentioned: Gemini, Gemini Enterprise Agent Platform, Cloud Run

Join Gemini Enterprise Agent Ready (GEAR) for the latest agent resources here. → https://goo.gle/3Srblgl Learn how to build a production-grade agent with Google's Agent Development Kit (ADK), the Model Context Protocol (MCP), and Gemini 3 Flash. Google Developer Expert, Jigyasa Grover showcases “Critics Cut,” a multilingual, context-aware AI assistant designed to eliminate the endless scrolling when looking for something to watch. Speakers: Jigyasa Grover Products Mentioned: Agent Development Kit, Model Context Protocol

Google Antigravity → https://goo.gle/4weoXdJ Getting started with Antigravity → https://goo.gle/4uV0Cbu Watch how a single voice prompt in Antigravity orchestrates a team of AI sub-agents to build a full-stack, multilingual note taking app from scratch. This complete project uses Vite for the front end, Go and SQLite for the backend, and Docker Compose to orchestrate the services. Watch along and discover how advanced tools like Chrome MCP and the modern web guidance enable seamless code generation, markdown preview rendering, and local testing. Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speakers: Rody Davis, Shir Meir Lador Products Mentioned: Gemini, Antigravity

Google Antigravity → https://goo.gle/4oRqZhk Getting started with Antigravity → https://goo.gle/4g2iZaU Check out how Rody Davis used Gemini and Antigravity to build a serverless, VS Code-styled website generator featuring theme switching and offline vector search. By leveraging Gemma to summarize posts and embedding-gemma to vectorize content at compile time, this static site serves dynamic recommendations completely offline. Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speakers: Rody Davis, Shir Meir Lador Products Mentioned: Gemini, Antigravity

Github repo → https://goo.gle/multiagent When you have 100 AI agents across your org, how do they find and talk to each other? This is how: the Agent2Agent (A2A) Protocol and Agent Registry. In this episode of Hands On AI, we build a production-ready multi-agent system. We start with the Agent2Agent (A2A) Protocol, think "HTTP for AI agents", then solve agent sprawl with Agent Registry, so your agents discover each other instead of hard-coding URLs. We build it live with a dog walker agent and a trip planner agent on Google's Agent Development Kit (ADK), then orchestrate them together. What you'll learn: * What the A2A protocol is, and when to use it for multi-agent systems. * Agent cards — an agent's "LinkedIn profile" for discovery. * Sync vs async agent communication (polling vs streaming). * Wrapping an ADK agent as an A2A remote agent with to_a2a. * The agent sprawl problem — and how Agent Registry solves it (reusability, one way to connect, governance). * Registering agents via gcloud and the Cloud console. * Using Agent Registry's MCP server to discover agents + tools dynamically — no more hard-coded URLs. * Bringing in third-party agents (LangGraph, CrewAI) and MCP servers. Chapters: 00:00 - Intro: Agent2Agent (A2A) Protocol & Agent Registry 03:06 - What Is Agent2Agent (A2A) Protocol? (HTTP for AI agents) 04:29 - When & why to use A2A 06:31 - Agent cards: An agent's LinkedIn profile 09:34 - Sync vs async communication 11:20 - Demo: building a dog walker agent (ADK) 15:21 - Wrapping an agent as an A2A remote agent 17:20 - Connecting two agents with A2A 19:27 - The problem: Agent sprawl 20:05 - What is Agent Registry? 22:35 - Registering agents (gcloud + console) 27:13 - Beyond agents: MCP servers & endpoints 29:18 - Connecting through the registry — No more hard-coded URLs 35:36 - Demo: The orchestrator agent 41:09 - Authentication & wrap up More resources: Google Agent Development Kit (ADK) → https://goo.gle/3PItVzL Agent Runtime → https://goo.gle/4nXDhnX Agent Registry / Agent Platform → https://goo.gle/4aZAdlM Agent2Agent Protocol (A2A) protocol → https://goo.gle/4u5x8HF Sita Lakshmi on LinkedIn → https://goo.gle/3QyQzLl Annie Wang on LinkedIn → https://goo.gle/43GCXAo Watch more Hands on AI → https://www.youtube.com/playlist?list=PLIivdWyY5sqKnJOvP89yF8t9mWuzMTcbM 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Sita Lakshmi, Annie Wang Products Mentioned: Google Agent Development Kit, Gemini API, Agent Runtime, AgentRegistry, Agent2Agent (A2A) Protocol

Google Antigravity → https://goo.gle/4ewS7P6 Getting started with Antigravity → https://goo.gle/4xKK6Oh Do you lose your GitHub repositories and local files across multiple projects? Watch along as Rody Davis explains how he used Antigravity to automate file system workflows based on time boxes and tags. Watch along and be inspired to boost your software development efficiency, reduce mental fatigue, and spend more time coding instead of searching for files. Watch more The Agent Factory: Developer Power-Ups → https://goo.gle/Supercharge-Devs 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #DeveloperPowerUps Speakers: Rody Davis Products Mentioned: Antigravity

The AI model is just the brain—the harness is what turns predictions into finished tasks. Google Developer Expert, Muhammad Farooq shares the 5 critical components every harness needs to separate a flashy demo from a real agent that actually ships. For more agent resources, join the Gemini Enterprise Agent Ready (GEAR) program → https://goo.gle/43vfVws Speakers: Muhammad Farooq Products Mentioned: Gemini

Discover the latest in data analytics agents. In this session, we’ll explore enhanced built-in capabilities designed to streamline workflows across data engineering, data science, and conversational analytics. Learn to build custom agents grounded in your enterprise data using new developer tools, including the Agent Development Kit (ADK) and Model Context Protocol (MCP) integrations. Find out how to access these powerful features seamlessly via the Gemini CLI, Claude Code, Codex, and IDEs like VSCode to supercharge your productivity. Watch more Google Cloud Next 2026 Sessions → https://goo.gle/gcloud-next-2026 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Manikandan Srinivasan, Ganesh Kumar Gella, Mauro Flores BRK2-037 #GoogleCloudNext

AI-native databases are essential for powering agents with enterprise data. Learn how they enable highly relevant context, automate operations, and manage risk. In this session, we’ll examine AI-powered search, natural language interfaces, multimodal queries, and graph retrieval-augmented generation (RAG). These move beyond simple retrieval, providing agents with high-fidelity, interconnected context. Discover how open standards like Model Context Protocol (MCP) and agentic IDEs streamline workflows for rapid, reliable deployment of agents. Watch more Google Cloud Next 2026 Sessions → https://goo.gle/gcloud-next-2026 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Amit Ganesh, Yannis Papakonstantinou, David Soria Parra BRK2-021 #GoogleCloudNext

Go beyond keyword search to get the most out of your operational data. In this session, learn to build sophisticated, AI-powered experiences with Spanner. Discover how to combine full-text and vector search into powerful multi-model queries that deeply understand user intent. We’ll unveil new AI innovations that simplify contextual search and retrieval-augmented generation (RAG) applications. Explore seamless integrations with Gemini Enterprise Agent Platform to create the next generation of contextual, intelligent, multi-model search. Watch more Google Cloud Next 2026 Sessions → https://goo.gle/gcloud-next-2026 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Jeff Sosa, Girish Baliga, Alexander Christie BRK3-054 #GoogleCloudNext

Join this session to learn about Agent Development Kit (ADK) and Model Context Protocol (MCP) integration methods that standardize how agents connect to your data while removing the need to build custom database connectors from scratch. Discover how to build agents with the ADK that accesses BigQuery for analysis, Google Maps for geospatial insights, and AlloyDB for transactions – all in a single workflow. Learn how to implement agent operations (AgentOps) for deep observability into both agent performance and cost with a single line of code. Watch more Google Cloud Next 2026 Sessions → https://goo.gle/gcloud-next-2026 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech Speakers: Sandeep Karmarkar, Jiaxun Wu, Guillaume Blaquiere BRK2-048 #GoogleCloudNext