Rejoindre Se connecter

Dinesh Bhamare

Date d'abonnement : 2022

Ligue d'Or

10187 points
Agents d'IA générative : transformer l'entreprise Earned oct. 31, 2026 EDT
Evaluate and Improve Agent Development Kit Agents Earned oct. 31, 2026 EDT
Deploy an Agent with Agent Development Kit (ADK) Earned oct. 29, 2026 EDT
Craft ADK Agents with Persistent Memories Earned oct. 27, 2026 EDT
Traitement des données sans serveur avec Dataflow : développer des pipelines Earned oct. 27, 2026 EDT
Accelerate Development with Antigravity Earned oct. 26, 2026 EDT
Cost Estimation and Optimization for Agentic Solutions Earned oct. 15, 2026 EDT
Hill Climb Generative and Agentic Systems Earned oct. 15, 2026 EDT
Upgrade to the Latest Gemini Models Earned oct. 15, 2026 EDT
Evaluate Agents on Gemini platform Earned oct. 15, 2026 EDT
Evaluate Generative and Agentic Systems Earned oct. 15, 2026 EDT
Build Enterprise Agents with Code Execution on Gemini platform Earned oct. 15, 2026 EDT
Build Agents with the Agent Development Kit Earned oct. 15, 2026 EDT
Build with the Managed Agents API on Gemini platform Earned oct. 11, 2026 EDT
Accelerate Agent Development with Antigravity and Agents CLI Earned oct. 11, 2026 EDT
Applications d'IA générative : changez votre façon de travailler Earned juin 30, 2026 EDT
IA générative : se familiariser avec le domaine Earned juin 28, 2026 EDT
IA générative : découvrir les concepts fondamentaux Earned mai 13, 2026 EDT
IA générative : au-delà du chatbot Earned mai 12, 2026 EDT
Créer un guide d'étude pour une certification : préparation à l'examen PDE Earned mars 23, 2024 EDT

Agents d'IA générative : transformer l'entreprise est le cinquième et dernier cours du parcours de formation "Leader en IA générative". Il aborde la façon dont les entreprises peuvent utiliser des agents d'IA générative personnalisés pour relever des défis métier spécifiques. Des exercices pratiques vous apprendront à créer un agent d'IA générative de base tout en découvrant les composants de ces agents, comme les modèles, les boucles de raisonnement et les outils.

En savoir plus

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.

En savoir plus

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.

En savoir plus

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.

En savoir plus

Dans ce deuxième volet de la série de cours sur Dataflow, nous allons nous intéresser de plus près au développement de pipelines à l'aide du SDK Beam. Nous allons commencer par passer en revue les concepts d'Apache Beam. Nous allons ensuite parler du traitement des données par flux à l'aide de fenêtres, de filigranes et de déclencheurs. Nous passerons ensuite aux options de sources et de récepteurs dans vos pipelines, aux schémas pour présenter vos données structurées, et nous verrons comment effectuer des transformations avec état à l'aide des API State et Timer. Nous aborderons ensuite les bonnes pratiques qui vous aideront à maximiser les performances de vos pipelines. Vers la fin du cours, nous présentons le langage SQL et les DataFrames pour représenter votre logique métier dans Beam, et nous expliquons comment développer des pipelines de manière itérative à l'aide des notebooks Beam.

En savoir plus

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!

En savoir plus

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.

En savoir plus

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…

En savoir plus

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.

En savoir plus

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.

En savoir plus

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…

En savoir plus

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.

En savoir plus

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.

En savoir plus

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.

En savoir plus

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.

En savoir plus

Le cours "Applications d'IA générative : changez votre façon de travailler" est le quatrième du parcours de formation "Leader en IA générative". Ce cours présente les applications d'IA générative de Google, telles que Gemini pour Workspace et NotebookLM. Il vous guide à travers des concepts comme l'ancrage, la génération augmentée par récupération, la création de requêtes efficaces et la conception de workflows automatisés.

En savoir plus

IA générative : se familiariser avec le domaine est le troisième cours du parcours de formation "Gen AI Leader". L'IA générative change notre façon de travailler et d'interagir avec le monde autour de nous. En tant que responsable, comment pouvez-vous exploiter son potentiel pour obtenir des résultats commerciaux concrets ? Dans ce cours, vous allez découvrir les différentes couches qui composent une solution d'IA générative, les offres de Google Cloud et les facteurs à prendre en compte au moment de choisir une solution.

En savoir plus

IA générative : découvrir les concepts fondamentaux est le deuxième cours du parcours de formation "Leader en IA générative". Il vous permettra de découvrir les concepts fondamentaux de l'IA générative en examinant les différences entre l'IA, le ML et l'IA générative, mais aussi de comprendre comment l'IA générative permet de relever les défis de l'entreprise en utilisant différents types de données. Enfin, vous découvrirez les stratégies de Google Cloud pour gérer les limites des modèles de fondation et quelles sont les grandes problématiques du développement et du déploiement d'une IA responsable et sécurisée.

En savoir plus

Le cours IA générative : au-delà du chatbot est le premier du parcours de formation "Gen AI Leader" et n'a aucun prérequis. Il dépasse les principes de base des chatbots afin de présenter le véritable potentiel de l'IA générative pour votre organisation. Vous découvrirez des concepts tels que les modèles de fondation et le prompt engineering (ingénierie des requêtes), qui sont essentiels pour exploiter la puissance de l'IA générative. Ce cours vous aidera également à identifier les facteurs à prendre en compte pour développer une stratégie d'IA générative efficace pour votre entreprise.

En savoir plus

Découvrez comment utiliser Gemini Notebook pour créer un guide de préparation personnalisé pour l'examen de certification Professional Data Engineer. Vous allez passer en revue les fonctionnalités de Gemini Notebook, créer un notebook dans Gemini Notebook, et apprendre à utiliser un guide d'étude pour vous entraîner à passer un examen de certification.

En savoir plus