Raj Marathi
Member since 2026
Diamond League
22807 points
Member since 2026
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。
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。
本課程針對評估生成式和預測式 AI 模型,向機器學習從業人員介紹相關的基礎工具、技術和最佳做法。模型評估是機器學習的重要領域,確保這類系統能在正式環境中提供可靠、準確且成效優異的結果。 學員將深入瞭解多種評估指標與方法,以及適用於不同模型類型和工作的應用方式。此外,也會特別介紹生成式 AI 模型帶來的獨特難題,並提供有效的應對策略。透過 Google Cloud Vertex AI 平台,學員將瞭解在模型挑選、最佳化和持續監控方面,該如何導入穩健的評估程序。
While the traditional approaches of using data lakes and data warehouses can be effective, they have shortcomings, particularly in large enterprise environments. This course introduces the concept of a data lakehouse and the Google Cloud products used to create one. A lakehouse architecture uses open-standard data sources and combines the best features of data lakes and data warehouses, which addresses many of their shortcomings.
In this course you will get hands-on in order to work through real-world challenges faced when building streaming data pipelines. The primary focus is on managing continuous, unbounded data with Google Cloud products.
In the last installment of the Dataflow course series, we will introduce the components of the Dataflow operational model. We will examine tools and techniques for troubleshooting and optimizing pipeline performance. We will then review testing, deployment, and reliability best practices for Dataflow pipelines. We will conclude with a review of Templates, which makes it easy to scale Dataflow pipelines to organizations with hundreds of users. These lessons will help ensure that your data platform is stable and resilient to unanticipated circumstances.
完成進階的「部署多代理架構」技能徽章課程,證明您具備以下技能: 使用 ADK 建構多代理系統、將代理連結代理對代理 (A2A) 通訊協定、使用 Model Context Protocol (MCP) 整合外部工具,以及將完整的多代理解決方案部署至 Agent Engine。
完成「使用 Agent Development Kit (ADK) 建造 AI 代理:工程設計」技能徽章中階課程,即可證明您具備下列技能: 提出實際的語言模型研究問題、建構簡單的權杖化工具、準備資料集來訓練 Transformer 語言模型,以及執行小型語言模型的訓練迴圈。
將代理從 localhost 移至正式環境。本課程將說明如何將 ADK 代理部署至 Vertex AI Agent Engine 和 Cloud Run,並透過 Memory Bank 視情況啟用跨工作階段記憶。
運用 Google 的 Agent Development Kit (ADK) 和 Google Cloud 的強大基礎架構,探索多代理系統的架構和部署作業。您將學習設計階層式代理樹狀結構和確定性工作流程代理,同時找出理想的託管環境 (從無伺服器 Cloud Run 到高效能 GKE),確保您的 AI 代理安全、具備擴充性且可部署於正式環境。
完成運用 Gemini Enterprise 自動調度管理多代理工作流程技能徽章的入門課程,即可證明您具備下列技能:使用 Gemini Enterprise 支援的代理型助理,整合第一方和第三方來源的資料;開發多媒體行銷素材資源;以及自動執行跨系統的業務行動。技能徽章課程透過實作實驗室和挑戰評量,檢驗學員對於特定產品的實作知識。完成課程或直接進行挑戰實驗室,即可取得徽章。徽章可證明您的專業能力、提升專業形象,開創更多職涯發展機會。前往個人資料頁面,追蹤您獲得的徽章。
探索從任務導向工作流程到人本 AI 自動化調度管理的重要轉變。您將學習如何策略性區分擴增和自動化,以及如何平衡機器效率與人類直覺。
「生成式 AI 代理:實現組織轉型」是 Gen AI Leader 學習路徑的第五堂也是最後一堂課程。本課程將探討組織如何運用自訂生成式 AI 代理,解決特定的業務難題。您將動手練習建構基本的生成式 AI 代理,同時探索這類代理的各種元件,例如模型、推論迴圈和工具。
Close the gap between general AI capabilities and your domain knowledge through Agent Skills. This course walks you through the full lifecycle of custom skill building, from local scaffolding and testing to enterprise scaling and sharing using Google's agent ecosystem, including Google Antigravity, ADK, and Skill Registry. Additionally, you use Google Agents CLI toolkit to attach skills to standalone 24/7 cloud agents, equipping your team with reliable, autonomous digital coworkers.
瞭解如何使用 Google 的 Agent Development Kit (ADK) 和 Model Context Protocol (MCP),設計、協調及部署多代理系統。本課程將以旅遊規劃服務為例,說明如何透過自訂防護機制,調度管理專用代理網路。完成本課程後,您將瞭解如何運用設計模式和部署策略,打造穩固且可擴充的 AI 工作流程。
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。
As enterprise teams transition to autonomous AI agents, security evolves toward proactive, identity-centric protection. In this course, you will implement a zero-trust security architecture for Cymbal Banking's underwriting platform using the Gemini Enterprise Agent Platform. By deploying a regional Egress Agent Gateway, configuring Model Armor and Semantic Governance (SGP) safety templates, assigning cryptographic SPIFFE identities to agent runtimes, and declaring a VPC-SC perimeter in Terraform, you will protect database boundaries and manage tools with production-grade governance.
瞭解如何在 Google Cloud 保護及管理 AI 代理。本課程提供實用藍圖,協助您保護代理記憶、透過 IAM 和 VPC Service Controls 強制執行嚴格的存取控管,以及部署即時對話防護機制,確保企業部署安全且符合法規。
您已建構能回覆查詢的基本 LLM 代理,是時候讓代理有狀態。利用工作階段狀態建構能維持對話脈絡、記住使用者偏好,並提供個人化體驗的代理。將代理從無狀態的回覆者轉為智慧助理。 查看 Gemini Enterprise Agent Ready (GEAR) 計畫的其他內容。 加入社群論壇,提出問題並參與討論
您已經成功打造第一個代理,是時候迎接更進階的挑戰。在本課程中,您將學習如何應用進階指令、選擇模型、建立規劃能力及結構化輸出模式,藉此將基本 AI 代理轉為高明又精確的助理,讓您的技能更上一層樓。查看 Gemini Enterprise Agent Ready (GEAR) 計畫的其他內容。 加入社群論壇,提出問題並參與討論。
使用 Agent Development Kit (ADK) 建構、設定及執行您的第一個 AI 代理,將自身代理知識化為實際成果。 在這堂實作課程,您會設立完整的 ADK 開發環境,並使用 Python 程式碼和 YAML 設定打造代理,然後透過多個介面執行。您也會瞭解定義代理行為的核心參數,將課程 1 的學習成果轉化為實際運作的程式碼。 查看 Gemini Enterprise Agent Ready (GEAR) 計畫的其他內容。
您已建立具有進階設定功能的代理,可開始賦予代理實際應用能力。為代理配備工具,使代理能搜尋網路、執行程式碼、查詢資料庫和執行自訂動作。將代理從聰明的回覆者,轉變為能採取行動的得力助手。 查看 Gemini Enterprise Agent Ready (GEAR) 計畫的其他內容。 加入社群論壇,提出問題並參與討論。
建立您的第一個 Gemini Enterprise 應用程式,獲得技能徽章!將各種資料來源連接到您的應用程式,建立強大的統合式搜尋和分析引擎。掌握 Deep Research 代理、多代理構思和 NotebookLM 等進階功能,進行重點分析。
瞭解 AI 代理如何發揮更高的業務影響力,包括根據您的 KPI 規劃要使用的代理類型,以及探索能解決實際瓶頸的用途。您也將認識各種無程式碼到高程式碼解決方案,瞭解 Gemini Enterprise 如何協助建構和自動調度合適的代理。
本課程介紹 AI 代理的基礎知識,並探討代理的實際應用價值。代理可為開發人員、架構師和技術決策者奠定基礎,協助他們從目標導向的自主行為角度來理解 AI 系統。
This course is part 1 of a 3-course series on Serverless Data Processing with Dataflow. In this first course, we start with a refresher of what Apache Beam is and its relationship with Dataflow. Next, we talk about the Apache Beam vision and the benefits of the Beam Portability framework. The Beam Portability framework achieves the vision that a developer can use their favorite programming language with their preferred execution backend. We then show you how Dataflow allows you to separate compute and storage while saving money, and how identity, access, and management tools interact with your Dataflow pipelines. Lastly, we look at how to implement the right security model for your use case on Dataflow.
In this intermediate course, you will learn to design, build, and optimize robust batch data pipelines on Google Cloud. Moving beyond fundamental data handling, you will explore large-scale data transformations and efficient workflow orchestration, essential for timely business intelligence and critical reporting. Get hands-on practice using Dataflow for Apache Beam and Serverless for Apache Spark (Dataproc Serverless) for implementation, and tackle crucial considerations for data quality, monitoring, and alerting to ensure pipeline reliability and operational excellence. A basic knowledge of data warehousing, ETL/ELT, SQL, Python, and Google Cloud concepts is recommended.
本課程將示範如何在 BigQuery 運用 AI/機器學行模型,以執行生成式 AI 任務。透過涉及顧客關係管理的應用實例,您將瞭解運用 Gemini 模型解決業務問題的工作流程。為了便於理解,本課程還提供了採用 SQL 查詢和 Python 筆記本的程式設計解決方案,指導您逐步操作。
在本課程中,您會學到 Google Cloud 上的資料工程、資料工程師的角色與職責,以及這些內容如何對應至 Google Cloud 提供的服務。您也將瞭解處理資料工程難題的許多方法。
In this second installment of the Dataflow course series, we are going to be diving deeper on developing pipelines using the Beam SDK. We start with a review of Apache Beam concepts. Next, we discuss processing streaming data using windows, watermarks and triggers. We then cover options for sources and sinks in your pipelines, schemas to express your structured data, and how to do stateful transformations using State and Timer APIs. We move onto reviewing best practices that help maximize your pipeline performance. Towards the end of the course, we introduce SQL and Dataframes to represent your business logic in Beam and how to iteratively develop pipelines using Beam notebooks.
完成 透過 BigQuery 建構資料倉儲 技能徽章中階課程,即可證明您具備下列技能: 彙整資料以建立新資料表、排解彙整作業問題、利用聯集附加資料、建立依日期分區的資料表, 以及在 BigQuery 使用 JSON、陣列和結構體。
Learn how to use Gemini Notebook to create a personalized study guide for the Professional Data Engineer 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「使用 Knowledge Catalog 建構資料網格」技能徽章入門課程,即可證明您具備下列技能:使用 Knowledge Catalog 建構資料網格, 以利在 Google Cloud 維護資料安全性,並協助治理和探索資料。您將練習並測試自己的技能,包括在 Knowledge Catalog 為資產加上標記、指派 IAM 角色,以及評估資料品質。
這是 Google Cloud 資料分析專業證書五堂課程中的第二堂。本課程將帶您瞭解資料的結構化和組織方式。您將透過實作,瞭解資料湖倉架構和 BigQuery、Google Cloud Storage 與 DataProc 等雲端元件,有效率地儲存、分析及處理大型資料集。
這是 Google Cloud Data Analytics 專業證書五堂課程中的第五堂。在本課程中,您將結合第一到第四堂課程的基礎知識和技能,並活用所學,透過專題實作呈現完整的資料生命週期。您將練習使用雲端式工具,有效率地取得、儲存、處理、分析資料,並以圖表呈現及傳達資料洞察結果。本課程結束後,您將完成一項專案,證明自己精通於有效整理多個來源的資料、向不同相關人士說明解決方案,以及運用雲端式軟體將資料洞察結果以圖表呈現。此外,您還會更新履歷,並練習面試技巧,為應徵和面試做好準備。
這是 Google Cloud Data Analytics 專業證書五堂課程中的第四堂。本課程著重於培養雲端資料圖表製作的技能,共分五個主要階段:敘事、規劃、探索資料、建立圖表,以及與他人分享資料。您還會實際使用 UI/UX 技能,繪製具說服力的雲端原生圖表線框稿,並運用雲端原生資料圖表工具探索資料集、建立報表和資訊主頁,推動決策並促進協作。
Google Cloud 資料分析專業證書課程共有五堂課程,這是第三堂。本課程會先簡要說明資料歷程,從最初的資料收集,一直到最後的洞察分析。接著,您將依序學習如何使用 SQL 將原始資料轉換為可用的格式、怎麼透過資料管道轉換大量資料。最後,您將練習如何將轉換策略應用於實際資料集,滿足業務需求。
完成 在 Agent Platform 設計提示 技能徽章入門課程,即可證明您具備下列技能: 在 Agent Platform 設計提示、分析圖片,以及運用多模態模型生成內容。瞭解如何建立有效的提示、引導生成式 AI 輸出內容, 以及將 Gemini 模型用於實際的行銷情境。
完成使用 AppSheet 建構應用程式課程,即可獲得技能徽章 ,瞭解如何使用 AppSheet 建構、設定及發布應用程式。
完成在 Google 試算表使用函式、公式及圖表技能徽章中階課程, 即可證明您具備下列技能:運用函式分析資料、使用圖表呈現資料、設定資料格式,以及搜尋、 驗證與顯示資料。
完成「在連結試算表中分析 BigQuery 資料」技能徽章,即可證明您能使用連結試算表,在 Google 試算表中存取、分析及共用數十億列的 BigQuery 資料,還能以圖表呈現。
完成「實現雲端協作與生產力工作流」課程,即可獲得入門級技能徽章。本課程將介紹 Google 的協作平台, 帶您瞭解如何使用 Gmail、日曆、Meet、雲端硬碟、試算表和 AppSheet。
This course provides an introduction to Data Studio’s powerful features for data visualization and reporting. Learn to transform raw data into insightful reports by mastering various visualization options, connecting to diverse data sources, and implementing interactive controls such as filters. Explore data blending techniques to combine information from multiple sources and unlock deeper insights. Through hands-on exercises you'll gain the skills to create compelling, dynamic reports that effectively communicate data-driven stories.
This month's Arcade Sprint 4 is live! It's designed for quick learning. Since the labs are open all month, there's no rush; just jump in when you have the time. You'll earn 1 Arcade Point and a new skill with each step. It's that simple: grab your point and keep the momentum going!
This course is designed for data analysts who want to learn about using BigQuery for their data analysis needs. Through a combination of videos, labs, and demos, we cover various topics that discuss how to ingest, transform, and query your data in BigQuery to derive insights that can help in business decision making.
This month's Arcade Sprint 3 is live! It's designed for quick learning. Since the labs are open all month, there's no rush; just jump in when you have the time. You'll earn 1 Arcade Point and a new skill with each step. It's that simple: grab your point and keep the momentum going!
This month's Arcade Sprint 2 is live! It's designed for quick learning. Since the labs are open all month, there's no rush; just jump in when you have the time. You'll earn 1 Arcade Point and a new skill with each step. It's that simple: grab your point and keep the momentum going!
This month's Arcade Sprint 1 is live! It's designed for quick learning. Since the labs are open all month, there's no rush; just jump in when you have the time. You'll earn 1 Arcade Point and a new skill with each step. It's that simple: grab your point and keep the momentum going!
Welcome to Base Camp, where you’ll develop key Google Cloud skills (available in Spanish and Portuguese too!) and earn an exclusive credential that will open doors to the cloud for you. No prior experience is required!
Over 85% of enterprises are accelerating AI and cloud adoption to stay ahead. In this voyage, you’ll prepare and protect data using Dataprep and the Cloud Data Loss Prevention API, scan for vulnerabilities, and validate workloads. You’ll also build and deploy modern applications using Cloud Build, GKE pipelines, App Engine Flexible, and Artifact Registry — while creating AI-powered solutions with Vertex AI, Gemini, and Speech-to-Text. Together, these labs help you secure data, deploy confidently, and build intelligent cloud applications at scale.
Over 80% of security breaches are linked to misconfigurations and weak access controls — which is why mastering cloud security and automation matters. In this adventure, you’ll detect and investigate threats with Security Command Center, create IAM custom roles, and secure digital transactions using Confidential Space. You’ll also strengthen your data and infrastructure skills by working with Datastore, Pub/Sub, Cloud Storage APIs, data joins and warehousing techniques, load balancers, Terraform, and CI/CD pipelines with Jenkins on Kubernetes Engine. Together, these labs help you build secure, reliable, and scalable cloud environments with confidence.
Modern cloud teams rely on automation and strong platform knowledge to move faster and smarter. In this trail, you’ll deploy Kubernetes Load Balancers and Cloud SQL using Terraform, strengthen observability with Cloud Logging, and customize analytics experiences in Looker using Liquid. You’ll also put your knowledge to the test through role-based Arcade Quizzes — from Data Practitioner and Database Engineer to Workspace Administrator — sharpening both your technical confidence and real-world readiness.
Holi is all about bringing different colors together — and that’s exactly what this challenge does with technology. You’ll package applications with Docker, manage deployments using Kubernetes Engine, secure access with IAM and VPN, and deploy apps on App Engine. You’ll also store data in Cloud Storage and explore how AI APIs can analyze, classify, and translate text. It’s a hands-on way to see how different cloud pieces come together to build something reliable, secure, and smart.
Pup and Kit’s World Cup journey highlights how the right skills quietly power great experiences. As they plan, adapt, and stay in sync using data, automation, and cloud-based tools, the story nudges you to step into their shoes and build those capabilities yourself. Each lab mirrors a moment from their adventure, encouraging you to explore, experiment, and strengthen skills that help you stay prepared, move faster, and make smarter choices-whatever the situation demands.
Google Cloud Certifications provide a tangible way for you to demonstrate your skills to potential or current employers. These certifications incorporate performance-based questions, testing your hands-on expertise through practical tasks. Begin your journey towards becoming a Google Certified Professional with the help of the Arcade Cert Zone.
As Pup and Kit move through the city between matches—booking plans on the fly, exploring structures built to last, and navigating busy streets—the story reflects what it takes to keep systems running smoothly behind the scenes. From securing storage and shaping networks to improving performance, reliability, and cost efficiency, these labs echo the quiet work that makes flexibility possible. Along the way, hands-on challenges and quizzes sharpen decision-making, so when it’s time for the next big play, everything is ready to perform.
Developers using managed cloud services can reduce infrastructure management effort by up to 60%, allowing more time to focus on building features that matter. In this level, you’ll gain hands-on experience with Cloud SQL, containerized workloads, and cloud-native application development through the Arcade ACE App Dev series, helping you design, deploy, and manage scalable applications more efficiently.
Over 70% of cloud professionals say hands-on practice is the most effective way to build real-world skills. In this adventure, you’ll develop hands-on skills across data analytics, automation, security, networking, and application deployment using Google Cloud and Workspace tools. You’ll create dashboards and alerts in Looker, analyze security findings, work with AI-powered services, deploy CI/CD pipelines, and manage network access and traffic insights—strengthening your ability to design, monitor, and operate reliable, scalable cloud solutions.
本課程旨在提供必要的知識和工具,協助您探索機器學習運作團隊在部署及管理生成式 AI 模型時面臨的獨特挑戰,並瞭解 Vertex AI 如何幫 AI 團隊簡化機器學習運作程序,打造成效非凡的生成式 AI 專案。
This course empowers you to develop scalable, performant LookML (Looker Modeling Language) models that provide your business users with the standardized, ready-to-use data that they need to answer their questions. Upon completing this course, you will be able to start building and maintaining LookML models to curate and manage data in your organization’s Looker instance.
In this course, you learn how to do the kind of data exploration and analysis in Looker that would formerly be done primarily by SQL developers or analysts. Upon completion of this course, you will be able to leverage Looker's modern analytics platform to find and explore relevant content in your organization’s Looker instance, ask questions of your data, create new metrics as needed, and build and share visualizations and dashboards to facilitate data-driven decision making.
在本課程中,您將透過實際操作,瞭解如何在 Looker 應用進階 LookerML 概念。您將學習如何使用 Liquid 自訂和建立動態維度 和測量指標、建構動態 SQL 衍生資料表和自訂的原生衍生資料表, 並運用擴充參數將 LookML 程式碼模組化。
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。
本課程會說明 Gemini in BigQuery,這是一套由 AI 輔助的功能,可協助「從資料到 AI」的工作流程。這些功能包含資料探索和準備、程式碼生成和疑難排解,以及工作流程探索和視覺化。本課程將透過概念解說、應用實例和實作實驗室,協助資料從業人員提升工作效率,並加速開發 pipeline。
完成「為 Looker 資訊主頁和報表準備資料」技能徽章入門課程, 即可證明您具備下列技能:可篩選、排序和 pivot 資料、合併不同的 Looker 探索結果, 還能使用函式和運算子建構 Looker 資訊主頁和報表,取得資料分析結果和圖表。
瞭解如何在 Google Cloud 將原始數據轉化為明確的資料導向決策。本初級課程提供實作研究室和實際情境,引導您在 BigQuery 查詢資料、在 Looker 探索趨勢,以及透過數據分析工具製作可共用的互動式報表。
In this introductory course, you'll learn how Looker can help you explore, analyze, and visualize your data to drive better decisions. Through a combination of video lectures and demos, you'll discover how to connect to various data sources, build interactive dashboards, and perform effective data analysis. Whether you're a data analyst, BI analyst, data scientist or business user, this course will equip you with the foundational knowledge to start using Looker effectively, regardless of your background.
Welcome to Base Camp, where you’ll develop key Google Cloud skills (available in Spanish and Portuguese too!) and earn an exclusive credential that will open doors to the cloud for you. No prior experience is required!
這是 Google Cloud 資料分析專業證書五堂課程中的第一堂。在本課程中,您將瞭解雲端資料分析領域的定義,並說明雲端資料分析師在資料擷取、儲存、處理和視覺化方面的角色與職責。您將瞭解 BigQuery 和 Cloud Storage 等 Google Cloud 工具的架構,以及如何運用這些工具有效組織、呈現及彙整資料。
完成 從 BigQuery 資料取得深入分析結果 技能徽章入門課程,即可證明您具備下列技能: 撰寫 SQL 查詢、查詢公開資料表、將樣本資料載入 BigQuery、使用 BigQuery 的查詢驗證工具 排解常見語法錯誤,以及在 Data Studio 中 透過連結 BigQuery 資料建立報表。
完成「運用 BigQuery ML 建立機器學習模型」技能徽章中階課程,即可證明您具備下列技能: 可使用 BigQuery ML 建立及評估機器學習模型,並根據資料進行預測。