Skip to main content
AmigoFish

Google Cloud Tech

Google Cloud TechVideo

Format:
YouTube channel
New videos:
Daily
Typical length:
about 15 minutes, not counting Shorts
Latest video:
Not rated yet

About this show

Welcome to the official YouTube channel for Google Cloud’s technical community. Explore our tutorials, see exciting demos, stay up to date with product news, and find new developer tools helping you build what’s next.

Videos come from the channel's public YouTube feed. The artwork is the newest video thumbnail. Last updated . Names, artwork and text belong to their publishers.

Cosmos

Similar by topic and creator

See the full Cosmos

Videos

  • Tell your data story with Looker Data Apps

    · 2 min

    I built an interactive Looker Data App to tell you the story of some of the important pivots in my career with real data! With Looker Data Apps, you can create custom, interactive data applications all governed by LookML and hosted directly inside Looker. Drop a comment with what you're building with data apps! 👇 #Looker #GoogleCloud #BigQuery #DataApps #DevRel #CodingJourney

    Not rated yet
  • CodeMender: AI powered vulnerability fixes right in GitHub PRs

    · 6 min

    GitHub → https://g.dev/ai/gitops-starter-kit Learn how CodeMender uses AI to automate application security. By integrating directly into GitHub, CodeMender acts as a security gate, automatically scanning pull requests, blocking vulnerable code merges, verifying exploits in a sandbox, and proposing tested patches. Developers can review diffs, approve fixes, and patch vulnerabilities directly within their GitHub workflow. #GitHubSecurity #CodeMender #AISecurity #DevSecOps #CodeSecurity #AppSec #CyberSecurity #PullRequest #CloudSecurity #ShiftLeft #SSDLC Speaker: Manish Gaur Products Mentioned: CodeMender

    Not rated yet
  • An industry look into AI generated images & videos in fashion

    · 9 min

    Nano Banana tutorial → https://g.dev/ai/gemini-nano-banana Gemini Omni tutorial → https://g.dev/ai/flash-video-generation Join Google Cloud AI Developer Relations Engineer Katie Nguyen and Google Developer Expert Margaret Maynard-Reid as they explore the intersection of generative AI and fashion design. Fresh from New York Fashion Week, Margaret shares how designers are using Google’s latest generative media models, like Nano Banana and Omni 1.1 Flash, to prototype ideas, reduce industry waste, and streamline e-commerce workflows. Speakers: Katie Nguyen, Margaret Maynard-Reid Products Mentioned: Nano Banana, Gemini Omni

    Not rated yet
  • Before you vibe code: Build an AI app implementation plan

    · 11 min

    You have your design specs ready, but before you tell an AI agent to build your app, what comes next? In this episode of Build It, we walk through how to create a step-by-step implementation plan with zero coding required. Follow along as we prep our smart personal trainer app, turning our architecture docs into a crystal-clear execution roadmap so our agent never has to guess. Instead of rushing straight into building, learn how to act like an architectural detective. You will discover how to prompt Gemini to uncover missing requirements, resolve contradictions across design documents, and compare what the model assumes versus what it recommends. Plus, see how to structure a four-stage milestone plan with Antigravity, complete with human checkpoints, autonomous browser testing, and rollback version control so you can build with total confidence. Chapters: 0:00 - Intro 0:57 - Finding missing info and document contradictions 2:05 - Asking Gemini: Assumptions vs. recommendations 3:07 - Why updating specs in place preserves LLM context 4:00 - Creating backups to protect document integrity 5:15 - Structuring architecture docs for better model attention 6:53 - Why every AI app needs an implementation plan 7:29 - Breaking down the phase gated milestone approach 8:47 - Setting up human checkpoints and autonomous testing 10:06 - Adding version control and rollback safeguards More resources: Builder Central → https://g.dev/ai/builder-central Google Antigravity → https://g.dev/ai/build-it-with-agy Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleCloud #Gemini #Antigravity #NoCode #AIAgents #BuildIt Speaker: Devin Chase Products Mentioned: Gemini, Antigravity, Google Cloud

    Not rated yet
  • Security skills for AI agents (From Google security engineers)

    · 6 min

    Vibe code with confidence by securing your AI coding workflows to protect your secrets. In this video, we break down how to set up pre-commit and pre-tool hooks that stop coding agents from accidentally committing hardcoded API keys into Git history, as well as how to securely manage credentials with Google Cloud Secret Manager. Try Google Cloud Secret Manager → https://g.dev/cloud/cpm-vid-secret-mgr Check out security skills → https://g.dev/ai/github-agent-skills Chapters: 00:00 - Intro 00:20 - Preventing leaked API Keys in Git 01:06 - Pre-commit hooks for coding agents 01:49 - Storing credentials with Google Cloud Secret Manager 04:01 - Balancing security with developer velocity Speakers: Tilde Thurium, Aron Eidelman Products Mentioned: Secret Manager

    Not rated yet
  • AI agent memory

    · 42 sec

    Here is what most people get wrong about AI memory: they save the chat transcript. That is not memory. That is a log. Real memory has to separate two different things: • Facts (your name, your budget) → exact values that belong in a database • Meaning (“I like quiet, minimal things”) → understanding that belongs in vector memory That is the difference. Episode 5 shows how to design that memory system for any AI agent, using a live bidirectional multimodal agent as the example. #aiagents #aimemory #vectordatabase #multimodalai #llm Speaker: Annie Wang Products Mentioned: Gemini Live API

    Not rated yet
  • Why AI agents need their own identity & audit trails

    · 45 sec

    Until now, if an AI agent dropped a database table or sent an email, the audit log showed your username because it borrowed your credentials. Senior Developer Relations Engineer Smitha Kolan explains why autonomous AI coworkers need dedicated identity, governance, and traceability: * *Dedicated agent identity:* Stop running agents on borrowed human credentials so audit logs show exactly what the agent did. * *Inherited policy guardrails:* Gemini inherits your organization’s security policies, protocols, and operational limits across every surface. * End-to-end traceability:* Track and audit every action an autonomous agent takes, governed with the same rigor as an employee. Speaker: Smitha Kolan Products Mentioned: Gemini

    Not rated yet
  • Introducing the TPU agent suite (preview): Open source agents for PyTorch on Cloud TPU

    · 4 min

    Alongside TorchTPU, we’re releasing an early preview of the TPU agent suite on GitHub. Currently in preview for PyTorch inference workloads on Cloud TPUs, this open-source set of agents helps you onboard, profile, and serve models from inside the coding agent you already use. At launch, it works in Claude Code and Google Antigravity, with more coding agents to follow. You talk to one front-end agent (tpu-agent), which routes each task to a specialist sub-agent: tpu-model-onboarding helps bring a model up, benchmark it, or serve it; tpu-diagnostics captures and inspects profiles to find what is slowing a model down; tpu-kernel-development helps write and tune custom Pallas kernels; and tpu-knowledge-base answers hardware and software questions with a source you can check. Before onboarding runs, it shows you a plan for approval, and the serving workflow ends with a numerical parity check on the TPU against the original PyTorch model on CPU. The agents' actions are grounded, bounded, and checked, and you stay in the loop. The suite is open source and in preview on GitHub under google-pytorch. Chapters: 0:00 - Introduction 0:11 - TPUs, designed for machine learning 0:24 - TorchTPU: native PyTorch on Cloud TPU 0:35 - The TPU agent suite 0:47 - Works inside your coding agent 1:17 - From running to running well 1:44 - One front end, the right specialist for each job 2:29 - A serving example: the same checklist every time 3:04 - Three design choices 3:14 - Grounded: answers come with a source 3:23 - Bounded: a budget, then it hands back 3:41 - Checked: parity with plain PyTorch before it is called done 3:59 - Recap and getting started 🔗 Resources: * Explore the TPU agent suite on GitHub → https://g.dev/cloud/tpu-agent-suite * Explore TorchTPU on GitHub → https://g.dev/cloud/torch-tpu * PyTorch on Cloud TPU → https://g.dev/cloud/pytorch-on-tpu * Learn more about Google Cloud TPU → https://g.dev/cloud/tensor-processing-units Speaker: Rob Mulla Products Mentioned: Tensor Processing Units

    Not rated yet
  • AI Agent Memory Architecture: Structured SQL, Semantic Vector Search & Memory Bank

    · 12 min

    Code for this episode → https://g.dev/ai/fashion-mind In this episode, you'll learn the critical difference between Structured Facts and Semantic Understanding, why they should never live in the same database, what to do with raw audio/video perception, and how to read and write memory asynchronously without blocking latency-sensitive voice streams. Watch along and learn: * Short-Term (RAM) vs. Long-Term Agent Memory * Facts (Exact Lookup) vs. Understanding (Semantic Recall) * Why dumping exact facts into a vector store breaks your agent * Where to store Structured Memory (PostgreSQL, MySQL, Google Cloud SQL) vs. Semantic Memory (pgvector, AlloyDB, Vertex AI Agent Engine Memory Bank) * How to handle raw multimodal perception (camera frames & audio waveforms) * he Two-Track Read/Write Loop: Synchronous tool calls for facts vs. asynchronous off-the-hot-path extraction for understanding Chapters: 00:00 - Intro: What should a multimodal agent remember? 00:25 - Demo: Personal styling agent with long-term memory 00:53 - Short-term (RAM) vs. Long-term memory 01:28 - The 2 types of memory: Facts vs. understanding 02:29 - Where memory lives: SQL databases vs. vector stores 03:40 - Vector store options & managed memory bank 04:30 - Common mistake: Putting everything in a vector store 05:24 - What about raw perception? (Audio & video streams) 06:40 - How agents read memory at session start 07:38 - Saving memory: Fast sync writes vs. async extraction 08:44 - Keeping memory extraction off the live hot path 10:42 - Architecture recap & next episode: Real time vision 💬 Question of the day: What is the first thing you would want your AI agent to remember about you? Drop your answer in the comments below! 🔔 Subscribe and stay tuned for the next episode, where we give the agent eyes with real-time vision! Resources: Gemini Live API docs → https://g.dev/cloud/gemini-live Google Cloud SQL docs → https://g.dev/cloud/sql-docs AlloyDB docs → https://g.dev/cloud/alloydb-docs Vertex AI Agent Engine Memory Bank → https://g.dev/ai/scale-your-agents Follow Annie online: LinkedIn → https://goo.gle/annie-linkedin X → https://goo.gle/annie-x Watch more The Omni App → https://g.dev/cloud/modern-ai-app 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #AIAgents #MultimodalAI #SoftwareArchitecture #VectorDatabase #GoogleCloud #LLM #MachineLearning #AgenticAI #CloudSQL #VertexAI Speaker: Annie Wang Products Mentioned: Google Cloud SQL, AlloyDB, Vertex AI Agent Engine Memory Bank, Gemini Live API

    Not rated yet
  • What "one agent, everywhere you work" actually means

    · 38 sec

    What is the architectural difference between spinning up stateless chat tabs and working with one persistent cloud agent? Senior Developer Relations Engineer Smitha Kolan unpacks how Gemini operates as one dedicated agent across every surface you use: * *Beyond stateless chat tabs:* Replaces disconnected, siloed assistants with a single, always-on agent in the cloud. * *Cross surface routing:* Requests from Google Docs, your laptop, the mobile app, or the CLI all route to the exact same agent instance. * *One execution history:* Every surface reads and writes to one continuous memory and execution log, so context never gets lost. Speaker: Smitha Kolan Products Mentioned: Gemini

    Not rated yet

More in Technology

See all Technology shows