RITWICK BHARGAV
Mitglied seit 2025
Diamond League
11073 Punkte
Mitglied seit 2025
In this course, you'll learn to use the Agent Development Kit (ADK) 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 Enterprise 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 Enterprise Agent 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. And 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.
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 course, you’ll learn to simplify the creation of autonomous enterprise agents using the Agent Development Kit (ADK) 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.
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!
Mit dem Skill-Logo zum Kurs Analyse und Schlussfolgerungen mit multimodalen Daten anhand von Gemini weisen Sie fortgeschrittene Kenntnisse in den folgenden Bereichen nach: Gemini 2.0 Flash zum Analysieren von Text-, Bild-, Audio- (als Partituren) und Videodaten sowie zum Kombinieren dieser Informationen verwenden, um Schlussfolgerungen zu ziehen und Insights zu extrahieren.
Learn a variety of strategies and techniques to engineer effective prompts for generative models
Complete the Create media search and media recommendations applications with AI Applications skill badge to demonstrate your ability to create, configure, and access media search and recommendations applications using AI Applications. Please note that AI Applications was previously named Agent Builder, so you may encounter this older name within the lab content. 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!
Do you want to keep your users engaged by suggesting content they'll love? This course equips you with the skills to build a cutting-edge recommendations app using your own data with no prior machine learning knowledge. You learn to leverage AI Applications to build recommendation applications so that audiences can discover more personalized content, like what to watch or read next, with Google-quality results customized using optimization objectives.
Gemini Enterprise ist ein leistungsstarkes Tool, das das Fachwissen von Google in den Bereichen Suche und KI zusammenbringt. Mitarbeitende können damit bestimmte Informationen in Dokumentenspeichern, E‑Mails, Chats, Ticketsystemen und anderen Datenquellen über eine einzige Suchleiste finden. Der Gemini Enterprise-Assistent kann sie auch beim Brainstorming, der Recherche oder der Strukturierung von Dokumenten unterstützen und zum Beispiel Kollegen zu einem Kalendertermin einladen, um die Wissensarbeit und Zusammenarbeit zu beschleunigen. (Gemini Enterprise hieß früher Google Agentspace. In diesem Kurs kann es daher noch Verweise auf den alten Produktnamen geben.)
In this challenge lab, you will demonstrate your ability to add agents to a Gemini Enterprise app. 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 the Gemini Enterprise app.
This course provides learners the knowledge to configure Workforce Identity Federation to grant Google Cloud and Gemini Enterprise 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.
NotebookLM is an AI-powered collaborator that helps you do your best thinking. After uploading your documents, NotebookLM becomes an instant expert in those sources so you can read, take notes, and collaborate with it to refine and organize your ideas. NotebookLM Pro gives you everything already included with NotebookLM, as well as higher utilization limits, access to premium features, and additional sharing options and analytics.
Data stores represent a simple way to make content available to many types of generative AI applications, including search applications, recommendations engines, Gemini Enterprise apps, Agent Development Kit agents, and apps built with Google Gen AI or LangChain SDKs. Connect data from many sources include Cloud Storage, Google Drive, chat apps, mail apps, ticketing systems, third-party file storage providers, Salesforce, and many more.
This course introduces AI Applications. You will learn about the types of apps that you can create using AI Applications, the high-level steps that its data stores automate for you, and what advanced features can be enabled for Search apps. (Please note Gemini Enterprise was previously named Google Agentspace, there may be references to the previous product name in this course.)
Dieser Kurs behandelt die Grundlagen zu KI‑Agenten und zeigt, welchen Mehrwert sie für die Praxis bieten. Er bietet eine Wissensgrundlage für Personen in der Softwareentwicklung und -Architektur sowie für alle, die technische Entscheidungen fällen müssen und KI‑Systeme im Kontext von selbstständigen, zielorientierten Handlungen verstehen möchten.
Complete the Configure AI Applications to optimize search results skill badge to demonstrate your proficiency in configuring search results from AI Applications. You will be tasked with implementing search serving controls to boost and bury results, filter entries from search results and display metadata in your search interface. Please note that AI Applications was previously named Agent Builder, so you may encounter this older name within the lab content. 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!
This course covers techniques for boosting and filtering search results, as well as the implementation of meta tags for advanced search control.
AI Applications provides built-in analytics for your Agent Search and Gemini Enterprise apps. Learn what metrics are tracked and how to view them in this course.
Initial deployment of Agent Search and Gemini Enterprise apps takes only a few clicks, but getting the configurations right can elevate a deployment from a basic off-the-shelf app to an excellent custom search or recommendations experience. In this course, you'll learn more about the many ways you can customize and improve search, recommendations, and Gemini Enterprise apps.
Complete the Create and maintain Vertex AI Search data stores skill badge to demonstrate your proficiency in building various types of data stores used in Vertex AI Search applications. 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 Build search and recommendations AI Applications skill badge to demonstrate your proficiency in deploying search and recommendation applications through AI Applications. Additionally, emphasis is placed on constructing a tailored Q&A system utilizing data stores. Please note that AI Applications was previously named Agent Builder, so you may encounter this older name within the lab content. 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!
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.
This lab tests your ability to develop a real-world Generative AI Q&A solution using a RAG framework. You will use Firestore as a vector database and deploy a Flask app as a user interface to query a food safety knowledge base.
This course on Integrate Vertex AI Search and Conversation into Voice and Chat Apps is composed of a set of labs to give you a hands on experience to interacting with new Generative AI technologies. You will learn how to create end-to-end search and conversational experiences by following examples. These technologies complement predefined intent-based chat experiences created in Dialogflow with LLM-based, generative answers that can be based on your own data. Also, they allow you to porvide enterprise-grade search experiences for internal and external websites to search documents, structure data and public websites.
In this skill bagde, you will demonstrate your ability to use and compare models available in the Vertex AI Model Garden. You'll deploy a model to a Vertex AI Endpoint, query other models via their API, and use Vertex AI's Gen AI evaluation service to measure the performance of multiple models.
Complete the Extend Gemini with controlled generation and Tool use skill badge to demonstrate your proficiency in connecting models to external tools and APIs. This allows models to augment their knowledge, extend their capabilities and interact with external systems to take actions such as sending an email. 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!"
Mit dem Skill-Logo zum Kurs Daten für die Vorhersagemodellierung mit BigQuery ML vorbereiten weisen Sie fortgeschrittene Kenntnisse in folgenden Bereichen nach: Erstellen von Pipelines für die Datentransformation nach BigQuery mithilfe von Dataprep von Trifacta; Extrahieren, Transformieren und Laden (ETL) von Workflows mit Cloud Storage, Dataflow und BigQuery; und Erstellen von Machine-Learning-Modellen mithilfe von BigQuery ML.
Mit dem Skill-Logo zum Kurs ML-Modelle mit BigQuery ML erstellen weisen Sie fortgeschrittene Kenntnisse in folgendem Bereich nach: Erstellen und Bewerten von Machine-Learning-Modellen mit BigQuery ML, um Datenvorhersagen zu treffen.
Mit dem Skill-Logo zum Kurs Daten für ML-APIs in Google Cloud vorbereiten weisen Sie Grundkenntnisse in folgenden Bereichen nach: Bereinigen von Daten mit Dataprep von Trifacta, Ausführen von Datenpipelines in Dataflow, Erstellen von Clustern und Ausführen von Apache Spark-Jobs in Managed Service for Apache Spark sowie Aufrufen von ML-APIs, einschließlich der Cloud Natural Language API, Cloud Speech-to-Text API und Video Intelligence API.
In diesem Kurs werden wichtige Themen zu Datenschutz und Sicherheit beim Einsatz von künstlicher Intelligenz vorgestellt. Dabei lernen Sie, wie Sie mit Google Cloud-Produkten und Open-Source-Tools empfohlene Vorgehensweisen im Zusammenhang mit Datenschutz und Sicherheit beim Einsatz von KI umsetzen.
In diesem Kurs werden Konzepte in Bezug auf die Interpretierbarkeit und Transparenz von künstlicher Intelligenz vorgestellt. Sie erfahren, warum die Transparenz der KI für Entwickler-Teams wichtig ist. Dabei lernen Sie praktische Techniken und Tools kennen, mit denen Sie sowohl die Interpretierbarkeit als auch die Transparenz von Daten und KI-Modellen optimieren können.
In diesem Kurs werden Konzepte für die verantwortungsbewusste Anwendung von KI und KI-Grundsätze vorgestellt. Es werden Techniken behandelt, wie Sie Fairness und Verzerrung (Bias) in der Praxis erkennen sowie Verzerrung in KI- und ML-Anwendungen reduzieren können. Dabei lernen Sie, wie Sie mit Google Cloud-Produkten und Open-Source-Tools Best Practices für eine verantwortungsbewusste Anwendung von KI umsetzen.
Mit auf generativer KI basierenden Anwendungen, kurz GenAI-Anwendungen, werden Nutzerinteraktionen möglich, die es vor Large Language Models (LLMs) kaum gab. Wie können Sie als Anwendungsentwickler mit generativer KI interaktive, leistungsstarke Anwendungen in Google Cloud erstellen? In diesem Kurs lernen Sie etwas über Anwendungen, die auf generativer KI basieren, und erfahren, wie Sie Prompt-Design und Retrieval-Augmented Generation (RAG) nutzen können, um mit LLMs leistungsstarke Anwendungen zu entwickeln. Wir stellen Ihnen eine produktionsreife Architektur für auf generativer KI basierende Anwendungen vor und Sie erstellen eine Chat-Anwendung auf der Basis von LLMs und RAG.
Dieser Kurs gibt Machine-Learning-Anwendern alle grundlegenden Tools, Techniken und Best Practices zur Bewertung von generativen und prädiktiven KI-Modellen an die Hand. Die Modellbewertung ist ein wichtiger Schritt, bei dem geprüft wird, ob ML-Systeme in der Produktion zuverlässige, genaue und leistungsstarke Ergebnisse erzielen. Die Teilnehmer erwerben fundierte Kenntnisse über verschiedene Bewertungsmesswerte und -methoden und lernen, sie auf unterschiedliche Modelltypen und Aufgaben anzuwenden. Im Kurs wird schwerpunktmäßig auf die besonderen Herausforderungen generativer KI-Modelle eingegangen und es werden Strategien vorgestellt, wie sich diese effektiv bewältigen lassen. Die Teilnehmer lernen auf der Plattform Vertex AI von Google Cloud, robuste Bewertungsprozesse zur Auswahl, Optimierung und kontinuierlichen Überwachung des Modells zu implementieren.
In diesem Einführungskurs im Microlearning-Format wird untersucht, was Large Language Models (LLM) sind, für welche Anwendungsfälle sie genutzt werden können und wie die LLM-Leistung durch Feinabstimmung von Prompts gesteigert werden kann. Darüber hinaus werden Tools von Google behandelt, die das Entwickeln eigener Anwendungen basierend auf generativer KI ermöglichen.
In diesem Einführungskurs im Microlearning-Format wird erklärt, was generative KI ist, wie sie genutzt wird und wie sie sich von herkömmlichen Methoden für Machine Learning unterscheidet. Darüber hinaus werden Tools von Google behandelt, mit denen Sie eigene generative KI-Anwendungen entwickeln können.
Dieser Kurs vermittelt Ihnen das Wissen und die nötigen Tools, um die speziellen Herausforderungen zu erkennen, mit denen MLOps-Teams bei der Bereitstellung und Verwaltung von Modellen basierend auf generativer KI konfrontiert sind. Sie erfahren, wie KI-Teams durch Vertex AI dabei unterstützt werden, MLOps-Prozesse zu optimieren und mit Projekten erfolgreich zu sein, in denen generative KI zum Einsatz kommt.