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!
Terminez le cours intermédiaire Analyser des données multimodales et en tirer des conclusions avec Gemini pour recevoir un badge démontrant vos compétences dans les domaines suivants : utiliser Gemini 2.0 Flash pour analyser des textes, des images, des fichiers audio (représentés sous forme de partitions) et des vidéos, puis tirer des conclusions et extraire des informations à partir de ces données combinées.
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.
Combinez l'expertise de Google dans les domaines de la recherche et de l'IA grâce à Gemini Enterprise. Cet outil puissant est conçu pour aider les collaborateurs à trouver des informations précises dans des documents stockés, des e-mails, des conversations, des systèmes de suivi des demandes et d'autres sources de données, le tout grâce à une simple barre de recherche. L'assistant Gemini Enterprise peut également les aider à trouver des idées, faire des recherches, résumer des documents et exécuter des tâches comme inviter des collègues à un événement d'agenda pour faciliter la collaboration et l'exploitation des connaissances. (Veuillez noter que Gemini Enterprise s'appelait auparavant Google Agentspace ; il se peut donc que ce cours contienne des références à l'ancien nom du produit.)
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.)
Ce cours présente les principes de base des agents IA et explore les cas où ils apportent une réelle valeur. Il fournit des bases aux développeurs, aux architectes et aux décideurs techniques qui souhaitent comprendre les systèmes d'IA à travers le prisme du comportement autonome et orienté vers des objectifs.
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!"
Terminez le cours intermédiaire Ingénierie des données pour la modélisation prédictive avec BigQuery ML pour recevoir un badge démontrant vos compétences dans les domaines suivants : la création de pipelines de transformation des données dans BigQuery avec Dataprep by Trifacta ; l'utilisation de Cloud Storage, Dataflow et BigQuery pour créer des workflows ETL (Extract, Transform and Load) ; et la création de modèles de machine learning avec BigQuery ML.
Terminez le cours intermédiaire Créer des modèles de ML avec BigQuery ML pour recevoir un badge démontrant vos compétences dans les domaines suivants : la création et l'évaluation de modèles de machine learning avec BigQuery ML pour générer des prédictions de données.
Terminez le cours d'introduction Préparer des données pour les API de ML sur Google Cloud pour recevoir un badge démontrant vos compétences dans les domaines suivants : le nettoyage des données avec Dataprep by Trifacta, l'exécution de pipelines de données dans Dataflow, la création de clusters et l'exécution de jobs Apache Spark dans Managed Service for Apache Spark, et l'appel d'API de ML comme l'API Cloud Natural Language, l'API Google Cloud Speech-to-Text et l'API Video Intelligence.
Ce cours présente des points importants au sujet de la confidentialité et de la sécurité de l'IA. Vous découvrirez des méthodes pratiques et des outils pour mettre en place des pratiques recommandées de confidentialité et de sécurité de l'IA à l'aide de produits Google Cloud et d'outils Open Source.
Ce cours présente les concepts d'interprétabilité et de transparence de l'IA. Il explique en quoi la transparence de l'IA est importante pour les développeurs et les ingénieurs. Il explore des méthodes et des outils pratiques permettant d'atteindre l'interprétabilité et la transparence des modèles d'IA et des données.
Ce cours présente le concept d'IA responsable et les principes associés. Il met en avant des techniques permettant d'identifier des données équitables ou biaisées, et de limiter les biais lors de l'utilisation de l'IA/du ML. Vous découvrirez des méthodes pratiques et des outils pour mettre en place de bonnes pratiques d'IA responsable à l'aide des produits Google Cloud et des outils Open Source.
Les applications d'IA générative peuvent créer de nouvelles expériences utilisateur qu'il était quasiment impossible d'obtenir avant l'invention des grands modèles de langage (LLM). En tant que développeur d'applications, comment pouvez-vous utiliser l'IA générative pour créer des applications interactives et performantes sur Google Cloud ? Dans ce cours, vous allez découvrir les applications d'IA générative, et comment vous pouvez utiliser la conception de requêtes et la génération augmentée par récupération (RAG) pour créer des applications performantes à l'aide de LLM. Vous allez vous familiariser avec une architecture prête pour la production qui peut être utilisée pour les applications d'IA générative, et vous allez créer une application de chat basée sur des LLM et sur le RAG.
Ce cours apporte aux professionnels du machine learning les techniques, les bonnes pratiques et les outils essentiels pour évaluer les modèles d'IA prédictive et générative. L'évaluation des modèles est primordiale pour s'assurer que les systèmes de ML fournissent des résultats fiables, précis et de haut niveau en production. Les participants acquerront une connaissance approfondie de diverses métriques et méthodologies d'évaluation, ainsi que de leur application appropriée dans différents types de modèles et tâches. Le cours mettra l'accent sur les défis uniques posés par les modèles d'IA générative et proposera des stratégies pour les relever efficacement. Grâce à la plate-forme Vertex AI de Google Cloud, les participants apprendront à implémenter des processus d'évaluation rigoureux pour la sélection, l'optimisation et la surveillance continue des modèles.
Ce cours de micro-apprentissage, qui s'adresse aux débutants, explique ce que sont les grands modèles de langage (LLM). Il inclut des cas d'utilisation et décrit comment améliorer les performances des LLM grâce au réglage des requêtes. Il présente aussi les outils Google qui vous aideront à développer votre propre application d'IA générative.
Ce cours de micro-apprentissage, qui s'adresse aux débutants, explique ce qu'est l'IA générative, décrit à quoi elle sert et souligne ce qui la distingue des méthodes de machine learning traditionnel. Il présente aussi les outils Google qui vous aideront à développer votre propre application d'IA générative.
Dans ce cours, vous allez acquérir les connaissances et les outils nécessaires pour identifier les problématiques uniques auxquelles les équipes MLOps sont confrontées lors du déploiement et de la gestion de modèles d'IA générative. Vous verrez également en quoi Vertex AI permet aux équipes d'IA de simplifier les processus MLOps et de faire aboutir leurs projets d'IA générative.