prakash khuntia
Member since 2022
Gold League
13185 points
Member since 2022
Streaming high-velocity data is great, but only if your pipeline doesn't break under pressure. In this trail, you'll wire up Pub/Sub and Python Dataflow to stream live data straight into Cloud Storage, then lock the whole environment down. By encrypting keys with Cloud KMS, cataloging assets, and isolating networks with VPC Peering, you'll clear both challenge labs and prove you can build real-time data lakes that are as fast as they are secure.
This is intended for individuals who completed the Build with Gemini workshop to validate the knowledge gained in that workship and earn a Skill Badge
Great code shouldn't get bogged down by infrastructure headaches. In this voyage, you'll master modern deployment patterns by turning ideas into production-ready microservices. From generating dynamic files and decoupling services with Pub/Sub to deploying polyglot apps across three different languages on App Engine, you'll cover the full developer lifecycle. Complete the challenge labs and show you know how to build fast, scale effortlessly, and keep things resilient.
Great teams don't just wing it—they execute a game plan. In this track, you'll captain your backend from the tactical board to the final whistle. Tune Spanner schemas for high-pressure traffic, whip pinpoint Pub/Sub messages across your services , and score clean API deployments with Cloud Run. Beat the challenge labs to claim your badge!
Welcome to this month's Arcade Simulator, where you'll step into the shoes of a DevOps Engineer tasked with keeping production environments fast, scalable, and resilient. You'll lay down a secure foundation with multi-VPC networks and access controls, then deploy multi-tier load balancers to distribute compute traffic seamlessly. Clear both challenge labs to prove you can automate, secure, and scale enterprise infrastructure without missing a beat.
In this focused course, you will learn how to improve Agent Search Results on the Gemini platform by mastering meta tags and serving controls. Through targeted lessons, hands-on labs, and quizzes, you will discover how to enrich your web content with metadata, schema.org JSON, and byline dates, and how to configure custom controls to boost, bury, and filter search results for a more relevant user experience. Explore other content in the Gemini Agent Ready (GEAR) program: https://developers.google.com/program/gear.
This course explores architecting stateful AI agents that use short-term memory within a session or long-term memory services. Additionally, it covers giving agents existing expertise through skills. It details the core pillars of context engineering to facilitate personalized, continuous conversational experiences with expert agents.
In this course, you’ll learn how to estimate and manage GenAI solution costs, focusing on the unique unit economics of AI versus traditional cloud billing. You will learn to: Understand Metering: Master the four Google Cloud GenAI metering categories and the token economy driving costs. Estimate Costs: Build defensible estimates using the Pricing Calculator for models, context caching, and agentic components. Optimize Spend: Leverage controls—such as input/output token reduction, caching, RAG efficiency, and model routing—while balancing cost, quality, and latency. Implement Governance: Apply FinOps best practices, including budgets, quotas, cost attribution, and Provisioned Throughput management to control spend.
In this course, you'll learn how to transition from anecdotal testing to a measurement-driven hill climbing process for generative and agentic systems. You'll explore how to balance output quality, latency, and operational cost by anchoring every change in baselines and evaluation rubrics. Using the hill climbing toolbox, you'll diagnose failures across models, prompts, tools, frameworks, and agent architectures. You'll analyze execution trajectories to identify root causes, design predictable tools using D.U.M.B. principles, and optimize retrieval-augmented generation (RAG) pipelines. When individual component tuning reaches diminishing returns, you'll learn how to restructure system architectures, using patterns like supervisor-worker, parallelization, and human-in-the-loop controls, to overcome performance plateaus. Finally, you'll explore how to automate the optimization loop to accelerate agent reliability while maintaining complete auditability and control in enterprise pro…
In this course, you'll learn how to establish a rigorous upgrade regression testing pipeline, safely deploy models using A/B testing and/or shadow mode, and address legacy prompt technical debt. You'll also learn the latest about Gemini 3 parameters including thinking levels and thought signatures, as well as new capabilities like media resolution controls and streaming function calls.
Welcome to Secure your Agents with Gemini Platform, a defense-in-depth course designed to help you establish centralized, zero-trust control over your AI workforce. You will learn to deploy Agent Gateway and Model Armor to manage agent sprawl, implement secure identity protocols like delegated identity and multi-legged OAuth flows, and set up advanced monitoring and observability. By the end, you will have the practical skills to build a secure, well-governed, and scalable agent ecosystem ready for enterprise-grade production. Explore other content in the Gemini Agent Ready (GEAR) program: https://developers.google.com/program/gear.
This course covers the technical side of governing an AI agent workforce using Agent Gateway, Agent Registry, and Policies. It discusses the overall architecture of centralized agent governance, focusing on managing agent sprawl and securing communication with internal systems. The course explores the infrastructure and enterprise networking required to deploy the Agent Gateway, including automated deployment with Terraform and configuring private egress via Private Service Connect. It offers guidance towards establishing a zero-trust security perimeter using unique agent identities with mTLS, per-tool authorization with REQUEST_AUTHZ, and granular CEL policies. Furthermore, it empowers administrators to implement content security guardrails using Model Armor in Gemini platform and Cloud DLP to mitigate semantic threats like prompt injection and data leakage. Finally, the course explains how to manage tool discovery through the Agent Registry and ensure end-to-end observability and thr…
In this challenge lab, you will demonstrate your ability to add agents to Gemini. You will build an agent with Agent Designer, and you will build a no-code agent with Agent Development Kit, deploy it to Agent Engine, and add it to Gemini.
In this challenge lab, you act as a Security Engineer deploying a secure Gemini environment for Cymbal Bank. You will ground Gemini in web search and internal Workspace sources to ensure accurate, contextual responses. To maintain compliance, you will configure Model Armor policies to filter sensitive data and block threats like prompt injections and malicious URLs. Finally, you will manage specific end-user features to customize the AI experience safely
Complete the Accelerate Development with Antigravity skill badge to demonstrate your proficiency in using the Antigravity IDE for developing agentic workflows. You will be tasked with configuring an MCP server, authoring custom agent skills and rules, prototyping with the Agents CLI, and deploying to the Google Cloud Agent Runtime. A skill badge is an exclusive digital badge issued by Google Cloud in recognition of your proficiency with Google Cloud products and services and tests your ability to apply your knowledge in an interactive hands-on environment. Complete the assessment challenge lab, to receive a skill badge that you can share with your network. When you complete this course, you can earn the badge displayed here and claim it on Credly! Boost your cloud career by showing the world the skills you have developed!
Complete the Evaluate and Improve Agent Development Kit Agents skill badge to demonstrate your ability to use ADK's evaluation tools to "hill climb" — making measurable, iterative improvements to an agent. You will run an initial evaluation to establish a baseline, apply optimization techniques, and re-evaluate the agent to measure your success.
In this challenge lab, you will demonstrate your ability to author agents using Agent Development Kit (ADK), deploy those agents to Agent Engine, and use them from a web app. Complete the challenge lab to earn a Google Cloud skill badge.
In this challenge lab, you will act as a cloud engineer supporting the Cymbal Pools finance team. Your mission is to deploy a BigQuery-enabled agent to Agent Runtime to help process invoice data using natural language. Rather than building from scratch, you inherit an unsecured deployment. You must establish basic data governance by configuring the Agent Development Kit (ADK), deploying the agent with a dedicated SPIFFE identity, identifying permission blocks, and applying least-privilege IAM roles so the agent can safely query and update the BigQuery database from the Agent Runtime Playground.
In this course, you explore the Code Execution feature of the Gemini platform, which lets AI agents safely generate and run Python code in isolated sandbox environments. You learn how the Agent Sandbox fits into the broader platform architecture, how to configure and operate Code Execution sandboxes using the Agent Platform SDK, and how to integrate code execution into agent workflows with the Agent Development Kit (ADK) in Gemini platform.
In this course, you learn to evaluate, diagnose, and optimize AI agents on the Gemini platform. You begin where most teams begin: the agent runs, but you have no eval cases, no test data, and no production traffic to grade it with. From there you follow the Quality Flywheel, the evaluate-analyze-optimize loop at the center of Gemini platform. You instrument the agent so it emits the telemetry Gemini platform reads, generate eval cases by simulation, choose the metrics that grade them, run offline evaluations, monitor live traffic and alert on quality drift, then cluster failures and optimize. A final module covers build-time evaluation with the Agent Development Kit (ADK) in Gemini platform, which runs on your machine before you deploy.
Deploying reliable generative and agentic systems requires moving beyond traditional software testing and subjective assessments. Because these probabilistic systems introduce unique failure modes, technical teams need structured frameworks to measure quality, enforce guardrails, and tie model behavior directly to business outcomes. Evaluate Generative and Agentic Systems gives engineers and architects practical tools to design, execute, and scale rigorous evaluation pipelines. You will master the full evaluation hierarchy, from fast deterministic checks to calibrated Large Language Model (LLM) autoraters and human-in-the-loop workflows. Learn how to simulate high-fidelity test datasets, trace multi-turn agent trajectories, and establish reliable consistency metrics across runs. By the end of this course, you will be prepared to translate organizational Key Performance Indicators (KPIs) into actionable technical benchmarks, calibrate objective rubrics, and maintain a continuous quali…
In this course, you'll learn to use the Agent Development Kit (ADK) in Gemini platform to build systems where multiple AI agents collaborate on complex tasks. You'll start with the ADK agent model: how ADK represents agents, tools, and runners, and how a single agent is configured and run. You'll then make tools the model can call, persist session state across agents, and instrument the execution lifecycle with callbacks and plugins. Next, you'll orchestrate multiple agents using ADK's template workflow agents and graph-based workflows, and ground them in enterprise data through multi-source retrieval and MCP integrations. Finally, you'll deploy a multi-agent system to Agent Runtime as a managed service and register and share it through Gemini so users across an organization can reach it.
In this course, you'll learn to build and run enterprise agents on the Managed Agents API, the managed agent runtime on Gemini platform. Three conceptual lessons give you the mental model. You'll learn why a real business task needs an agent rather than a chat model. You'll examine how the platform splits into a control plane that defines agents and a data plane that runs them. You'll learn how to assemble an agent from a definition, a sandboxed environment, mounted data, tools, and skills. Furthermore, you'll learn how to run it with background interactions, a streamed reason-act loop, resilient typed results, and state that persists across turns. You then put that model to work in a hands-on lab, where you build, run, and harden a retail merchandising agent for Cymbal Retail from an empty project to a production-shaped deployment. By the end, you'll be able to design, build, and operate a managed agent of your own.
本課程將複習 Model Armor 的基本安全功能,讓您具備使用這項服務的能力。您將瞭解 LLM 的相關安全風險,以及 Model Armor 如何保護 AI 應用程式。
This course provides learners the knowledge to configure Workforce Identity Federation to grant Google Cloud and Gemini access to users that authenticate using a third-party Identity Provider. The curriculum includes theory and demo videos covering workforce identity pools, OIDC and SAML providers, attribute mapping, IAM policies, and troubleshooting guidance.
This course covers the technical side of deploying Gemini. It discusses the overall architecture of Gemini, decisions to be made when provisioning the app infrastructure, and integrating enterprise data via Data Stores, Connectors. and Actions. The course also explores the kinds of agents that can be added to Gemini. It offers guidance towards establishing a security perimeter using IAM, VPC Service Control, Context-Aware Access, and semantic controls deployed with Model Armor in Gemini platform. Finally, it empowers administrators to fine-tune the end-user experience through comprehensive configuration options, and explains how administrators keep AI deployments secure, compliant, and performant through OpenTelemetry instrumentation and prompt logging.
This course will guide you through designing customer engagements that result in successful, well-utilized Gemini deployments. Study the art of change management, how to identify and engage sponsors, recruit early adopters, help your customer identify and address cultural change challenges and skills gaps, and effectively deliver project communications. Additionally, learn how to support your customer to plan, offer, conduct, and evaluate end-user training, leverage partner resources, and create essential project documents.
In this course, you’ll learn to simplify the creation of autonomous enterprise agents using the Agent Development Kit (ADK) in Gemini platform and you will learn how to leverage the power of Antigravity and the Agents CLI to transform your agent development workflow. In this course, you will explore practical techniques to automate repetitive tasks and significantly accelerate the creation of robust, enterprise-grade agents, ensuring scalability and efficiency in your AI projects.
A Business Leader in Generative AI can articulate the capabilities of core cloud Generative AI products and services and understand how they benefit organizations. This course provides an overview of the types of opportunities and challenges that companies often encounter in their digital transformation journey and how they can leverage Google Cloud's generative AI products to overcome these challenges.
完成 Looker 資料模型管理技能徽章中階課程,即可證明您具備下列技能:維護 LookML 專案的健全性、運用 SQL Runner 驗證資料、採用 LookML 最佳做法、改良查詢及 報表,並執行永久衍生資料表和快取政策。
Text Prompt Engineering Techniques introduces you to consider different strategic approaches & techniques to deploy when writing prompts for text-based generative AI tasks.
This content is deprecated. Please see the latest version of the course, here.
This course will help ML Engineers, Developers, and Data Scientists implement Large Language Models for Generative AI use cases with Vertex AI. The first two modules of this course contain links to videos and prerequisite course materials that will build your knowledge foundation in Generative AI. Please do not skip these modules. The advanced modules in this course assume you have completed these earlier modules.
本課程會介紹 Vertex AI Studio。您可以運用這項工具和生成式 AI 模型互動、根據商業構想設計原型,並投入到正式環境。透過身歷其境的應用實例、有趣的課程及實作實驗室,您將能探索從提示到正式環境的生命週期,同時學習如何將 Vertex AI Studio 運用在多模態版 Gemini 應用程式、提示設計、提示工程和模型調整。這個課程的目標是讓您能運用 Vertex AI Studio,在專案中發揮生成式 AI 的潛能。
本課程說明如何使用深度學習來建立圖像說明生成模型。您將學習圖像說明生成模型的各個不同組成部分,例如編碼器和解碼器,以及如何訓練和評估模型。在本課程結束時,您將能建立自己的圖像說明生成模型,並使用模型產生圖像說明文字。
這堂課程將說明變換器架構,以及基於變換器的雙向編碼器表示技術 (BERT) 模型,同時帶您瞭解變換器架構的主要組成 (如自我注意力機制) 和如何用架構建立 BERT 模型。此外,也會介紹 BERT 適用的各種任務,像是文字分類、問題回答和自然語言推論。課程預計約 45 分鐘。
本課程概要說明解碼器與編碼器的架構,這種強大且常見的機器學習架構適用於序列對序列的任務,例如機器翻譯、文字摘要和回答問題。您將認識編碼器與解碼器架構的主要元件,並瞭解如何訓練及提供這些模型。在對應的研究室逐步操作說明中,您將學習如何從頭開始使用 TensorFlow 寫程式,導入簡單的編碼器與解碼器架構來產生詩詞。
本課程將介紹注意力機制,說明這項強大技術如何讓類神經網路專注於輸入序列的特定部分。此外,也將解釋注意力的運作方式,以及如何使用注意力來提高各種機器學習任務的成效,包括機器翻譯、文字摘要和回答問題。
Earn a skill badge by passing the final quiz, you'll demonstrate your understanding of foundational concepts in generative AI. A skill badge is a digital badge issued by Google Cloud in recognition of your knowledge of Google Cloud products and services. Share your skill badge by making your profile public and adding it to your social media profile.
這個入門微學習課程主要介紹「負責任的 AI 技術」和其重要性,以及 Google 如何在自家產品中導入這項技術。本課程也會說明 Google 的 7 個 AI 開發原則。
這是一堂入門級的微學習課程,旨在探討大型語言模型 (LLM) 的定義和用途,並說明如何調整提示來提高 LLM 成效。此外,也會介紹多項 Google 工具,協助您自行開發生成式 AI 應用程式。
本課程將介紹擴散模型,這是一種機器學習模型,近期在圖像生成領域展現亮眼潛力。概念源自物理學,尤其深受熱力學影響。過去幾年來,在學術界和業界都是炙手可熱的焦點。在 Google Cloud 中,擴散模型是許多先進圖像生成模型和工具的基礎。課程將介紹擴散模型背後的理論,並說明如何在 Vertex AI 上訓練和部署這些模型。
隨著企業持續擴大使用人工智慧和機器學習,以負責任的方式發展相關技術也日益重要。對許多企業來說,談論負責任的 AI 技術可能不難,如何付諸實行才是真正的挑戰。如要瞭解如何在機構中導入負責任的 AI 技術,本課程絕對能助您一臂之力。 您可以從中瞭解 Google Cloud 目前採取的策略、最佳做法和經驗談,協助貴機構奠定良好基礎,實踐負責任的 AI 技術。
這個入門微學習課程主要說明生成式 AI 的定義和使用方式,以及此 AI 與傳統機器學習方法的差異。本課程也會介紹各項 Google 工具,協助您開發自己的生成式 AI 應用程式。
Learn how to use Gemini Notebook to create a personalized study guide for the Professional Cloud Architect certification exam. You'll review Gemini Notebook features, create a notebook in Gemini Notebook, and learn how to use a study guide to practice for a certification exam.
完成「設定 Google Cloud 網路」課程,即可獲得技能徽章。 您將瞭解如何在 Google Cloud Platform 執行基本的網路工作,包括建立自訂網路、新增子網路防火牆規則,還有建立 VM 並測試 VM 之間的通訊延遲。
只要修完「在 Google Cloud 設定應用程式開發環境」課程,就能獲得技能徽章。 在本課程中,您將學會如何使用以下技術的基本功能,建構和連結以儲存空間為中心的雲端基礎架構:Cloud Storage、Identity and Access Management、Cloud Functions 和 Pub/Sub。
完成「在 Google Cloud 使用 Terraform 建構基礎架構」技能徽章中階課程, 即可證明自己具備下列知識與技能:使用 Terraform 的基礎架構即程式碼 (IaC) 原則、運用 Terraform 設定佈建及管理 Google Cloud 資源、有效管理狀態 (本機和遠端),以及將 Terraform 程式碼模組化,以利重複使用和管理。
完成 建立 Google Cloud 網路 課程即可獲得技能徽章。這個課程將說明 部署及監控應用程式的多種方法,包括查看 IAM 角色及新增/移除 專案存取權、建立虛擬私有雲網路、部署及監控 Compute Engine VM、編寫 SQL 查詢、在 Compute Engine 部署及監控 VM,以及 使用 Kubernetes 透過多種方法部署應用程式。
這堂課程可讓參加人員瞭解如何使用確實有效的設計模式,在 Google Cloud 中打造相當可靠且效率卓越的解決方案。這堂課程接續了「設定 Google Compute Engine 架構」或「設定 Google Kubernetes Engine 架構」課程的內容,並假設參加人員曾實際運用上述任一課程涵蓋的技術。這堂課程結合了簡報、設計活動和實作研究室,可讓參加人員瞭解如何定義業務和技術需求,並在兩者之間取得平衡,設計出相當可靠、可用性高、安全又符合成本效益的 Google Cloud 部署項目。
Learn how to use Gemini Notebook to create a personalized study guide for the Professional Cloud Security Engineer certification exam. You'll review Gemini Notebook features, create a notebook, and learn how to use a study guide to practice for the certification exam.
各種規模的機構都開始運用雲端的強大功能和靈活性,徹底改變營運方式。不過,有效管理及擴充雲端資源可能是相當複雜的工作。本課程將探討在雲端中的現代營運、可靠性和韌性的基礎概念,以及 Google Cloud 如何協助您達成這些目標。本課程是 Cloud Digital Leader 學習路徑的一部分,旨在促進個人職能發展,並打造企業的未來。
許多傳統企業使用舊版系統和應用程式,無法滿足現今客戶的期望。企業主管經常需要在維護老舊的 IT 系統,以及投資新產品/服務之間做出選擇。本課程將探討這些挑戰,並提供解決方案,說明如何運用雲端技術克服難題。 本課程是 Cloud Digital Leader 學習路徑的一部分,旨在促進個人職能發展,並打造企業的未來。
雲端技術是強大的資產,與資料搭配後,將成為創新和提升客戶體驗的催化劑。「運用 Google Cloud 探索資料轉換功能」課程將探討機構如何運用雲端,讓資料更易於存取、做為行動依據和更有價值。 這門課程是 Cloud Digital Leader 學習路徑的一部分,旨在協助個人在職務上成長,並打造企業的未來。
數位轉型是現代組織必經的關鍵旅程,而建立穩固的雲端運算基礎,是跨出有意義創新的第一步。本課程「透過 Google Cloud 進行數位轉型」,將會介紹核心技術和策略框架,協助組織革新營運方式,並探討基本的雲端概念、全球網路基礎架構和共同責任模式,幫助主管在雲端之路上自信前行。本課程是 Cloud Digital Leader 學習路徑的一部分,旨在促進個人職能發展,並打造企業的未來。
Welcome to the two-part course on Logging, Monitoring, and Observability in Google Cloud. The core operations tools in Google Cloud break down into two major categories. The operations-focused components and the application performance management tools. This course, Logging and Monitoring in Google Cloud, covers the operations-focused components including Logging, Monitoring, and Service Monitoring. After taking this course, it is suggested that you complete part 2, Observability in Google Cloud, to learn about the available application performance management tools.
完成 Google Kubernetes Engine 成本效益最佳化 技能徽章中階課程, 即可證明您具備下列技能:建立及管理多租戶叢集、依據命名空間監控資源使用量、 設定自動調度叢集和 Pod 資源以提升效能、設定負載平衡以最佳化 資源分配,以及導入有效性和完備性探測,確保應用程式維持健康並符合成本效益。
歡迎參加「開始使用 Google Kubernetes Engine」課程。Kubernetes 是位於應用程式和硬體基礎架構之間的軟體層。如果您對這項技術感興趣,這堂課程可以滿足您的需求。有了 Google Kubernetes Engine,您就能在 Google Cloud 中以代管服務的形式使用 Kubernetes。 本課程的目標在於介紹 Google Kubernetes Engine (常簡稱為 GKE) 的基本概念,以及如何將應用程式容器化,以便在 Google Cloud 中執行。課程首先會初步介紹 Google Cloud,隨後簡介容器、Kubernetes、Kubernetes 架構和 Kubernetes 作業。
這堂隨選密集課程會向參加人員說明 Google Cloud 提供的全方位彈性基礎架構和平台服務,並將重點放在 Compute Engine。這堂課程結合了視訊講座、示範和實作研究室,可讓參加人員探索及部署解決方案元素,例如網路、系統和應用程式服務等基礎架構元件。另外,這堂課也會介紹如何部署實用的解決方案,包括客戶提供的加密金鑰、安全性和存取權管理機制、配額與帳單,以及資源監控功能。
這堂隨選密集課程會向參加人員說明 Google Cloud 提供的全方位彈性基礎架構和平台服務。這堂課結合了視訊講座、示範和實作研究室,可讓參加人員探索及部署解決方案元素,包括安全地建立互連網路、負載平衡、自動調度資源、基礎架構自動化,以及代管服務。
這堂隨選密集課程會向參加人員說明 Google Cloud 提供的全方位彈性基礎架構和平台服務,尤其側重於 Compute Engine。這堂課程結合了視訊講座、示範和實作研究室,可讓參加人員探索及部署解決方案元素,例如網路、虛擬機器和應用程式服務等基礎架構元件。您會瞭解如何透過控制台和 Cloud Shell 使用 Google Cloud。另外,您也能瞭解雲端架構師的職責、基礎架構設計方法,以及具備虛擬私有雲 (VPC)、專案、網路、子網路、IP 位址、路徑和防火牆規則的虛擬網路設定。
「Google Cloud 基礎知識:核心基礎架構」介紹了在使用 Google Cloud 時會遇到的重要概念和術語。本課程會透過影片和實作實驗室,介紹並比較 Google Cloud 的多種運算和儲存服務,同時提供重要的資源和政策管理工具。