En este curso, explorarás tecnologías, herramientas y aplicaciones de búsqueda potenciadas por IA. Aprende sobre las búsquedas semánticas utilizando embeddings de vectores, acerca de las búsquedas híbridas combinando enfoques semánticos y de palabras clave, y sobre la generación mejorada por recuperación (RAG) minimizando las alucinaciones como un agente de IA fundamentado. Adquiere experiencia práctica con Vector Search de Vertex AI para desarrollar tu motor de búsqueda inteligente.
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.
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!
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’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 the disciplined process of hill climbing to transform your generative and agentic systems into reliable, high-performing tools. You'll examine the iterative 8-step loop by diagnosing system failures through trajectory analysis and applying precise interventions across the model, prompt, tool, and framework layers. By the end of this course, you'll be prepared to optimize system architecture and automate the hill climbing cycle while balancing quality, cost, and latency as first-class metrics.
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.
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.
Throughout this course, you'll learn how to establish rigorous evaluation criteria, perform evaluations, design objective rubrics, calibrate autoraters, and simulate evaluation data. You'll gain the skills needed to design, execute, and scale a comprehensive evaluation plan that aligns system capabilities with organizational KPIs. This course is designed for technical practitioners, machine learning engineers, and software architects who build and deploy generative and agentic applications.
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.
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.
Completa la insignia de habilidad intermedia del curso Explora la IA generativa en Agent Platform y demuestra tus habilidades para realizar las siguientes actividades: generar texto, analizar imágenes y videos para crear contenido mejorado y aplicar técnicas de llamadas a funciones en la API de Gemini. Descubre cómo aprovechar las sofisticadas técnicas de Gemini, explorar la generación de contenido multimodal y expandir las capacidades de tus proyectos potenciados por IA.
El objetivo de este curso es equiparte con los conocimientos y las herramientas que necesitas para descubrir los desafíos únicos que enfrentan los equipos de MLOps cuando implementan y administran modelos de IA generativa, y explorar cómo Vertex AI fortalece a los equipos de IA para optimizar los procesos de MLOps y alcanzar el éxito en los proyectos de IA generativa.
En este curso, se presentan los conceptos de la IA responsable y los principios de la IA. Se abordan técnicas para identificar de forma práctica la equidad y los sesgos, y mitigar los sesgos en las prácticas de IA/AA. Se exploran métodos y herramientas funcionales para implementar prácticas recomendadas de la IA responsable con productos de Google Cloud y herramientas de código abierto.
Gemini para Google Workspace les proporciona a los clientes funciones potenciadas por IA generativa en Google Workspace. En esta ruta de aprendizaje, aprenderás sobre las funciones clave de Gemini y cómo se pueden usar para mejorar la productividad y eficiencia en Google Workspace.
Este curso les proporciona a los usuarios finales aprendizajes esenciales sobre las funciones principales, las características, los informes y, también, la información de configuración más relevantes según el rol. Este curso está especialmente dirigido a personas a cargo de funciones administrativas para respaldar la operación del centro de contacto, así como de analizar, solucionar problemas y configurar la plataforma para satisfacer mejor las demandas de los clientes. Si bien se abordarán algunos aspectos sobre informes y supervisión en este programa, esos temas se exploran en profundidad en el curso llamado “Administra informes y funciones con CCAIP”.
Este curso les brinda a los usuarios finales entrenamiento esencial sobre información básica relacionada con las funciones, la funcionalidad, la supervisión, los informes y la configuración más relevantes para sus roles. Este curso está especialmente dirigido a los responsables de los centros de contacto que tienen la tarea de supervisar la efectividad, la eficiencia y el cumplimiento de los KPI en todas las interacciones con los consumidores. Aunque en este programa se revisarán algunos aspectos relacionados con los parámetros y las opciones de configuración, se enfoca principalmente en las funciones de informes que proporciona la plataforma de CCAI.
En este curso, se les enseña a los agentes de centros de contacto sobre las principales características y funcionalidades de Contact Center AI Platform (CCAIP). CCAIP es una plataforma de centro de contacto unificada que acelera las capacidades de las organizaciones para usar y, luego, implementar CCAI sin depender de múltiples proveedores de tecnología. Este curso está especialmente dirigido a personas que se encargan de gestionar interacciones con los consumidores a través de chat y llamadas.
Combina la experiencia en la búsqueda y la IA de Google con Gemini Enterprise, una herramienta potente diseñada para ayudar a los empleados a encontrar información específica en almacenes de documentos, correos electrónicos, chats, sistemas de tickets y otras fuentes de datos, todo desde una sola barra de búsqueda. El asistente de Gemini Enterprise también puede ayudarte a generar ideas, investigar, crear esquemas de documentos y realizar acciones como invitar a compañeros de trabajo a un evento de calendario para acelerar el trabajo de conocimiento y la colaboración de todo tipo. (Ten en cuenta que Gemini Enterprise antes se llamaba Google Agentspace, por lo que puede haber referencias al nombre anterior del producto en este curso).
Demonstrate the ability to create and deploy generative virtual agents with natural language using Vertex AI Agent Builder and augment responses by integrating Gemini responses with third party APIs and your own data stores You will use the following technologies and Google Cloud services: Vertex AI Agent Builder Gemini Cloud Functions
In this course, you will learn about advanced methods and tools to monitor the performance of your Conversational agent in Conversational Agents. Please note Dialogflow CX was recently renamed to Conversational Agents and this course is in the process of being updated to reflect the new product name for Dialogflow CX.
Explore the Generative AI features for Conversational Agents and how to incorporate them into stateful Flows. Discover the possibilities with Generators, Generative Fallback, and Data Stores, as well as best practices and security settings for using these features.
This course will equip you with the tools to develop complex conversational experiences in Conversational Agents capable of identifying the user intent and routing it to the right self service flow.
This course explores advanced technical considerations to optimize Webhook connectivity for comprehensive, end-to-end, Conversational Agent self-service experiences. Please note Dialogflow CX was recently renamed to Conversational Agents, Virtual agent renamed to Conversational agent, and CCAI Insights were renamed to Conversational Insights, and this course is in the process of being updated to reflect the new product names for Dialogflow CX, and Virtual Agent, CCAI Insights.
Explore Playbooks and their implementation of the ReAct pattern for building conversational agents. You will learn how to construct a Playbook, set up goals and instructions to build a chatbot in natural language, and learn to test and deploy your solution.
This course will equip you with the tools to develop complex conversational experiences in Conversational Agents capable of identifying the user intent and routing it to the right self service flow. Please note Dialogflow CX was recently renamed to Conversational Agents, Virtual agent renamed to Conversational agent, and CCAI Insights were renamed to Conversational Insights, and this course is in the process of being updated to reflect the new product names for Dialogflow CX, and Virtual Agent, CCAI Insights.
Learn about building conversational AI voice and chat integrations, including how telephony systems can connect with Google to enable phone-based interactions within the Conversational AI ecosystem. Explore key topics such as the differences between chat and voice conversations, the writing process for creating conversation scripts, and the beginning of the interrogative series and closing sequence.
Demonstrate the ability to create and deploy deterministic virtual agents using Dialgflow CX and augment responses by grounding results on your own data integrating with Vertex AI Agent Builder data stores and leveraging Gemini for summarizations. You will use the following technologies and Google Cloud services: Vertex AI Agent Builder Dialogflow CX Gemini
In this course, you'll learn to develop AI agents that answer questions using websites, documents, or structured data. You will explore AI Applications and understand the advantages of data store agents, including their scalability and security. You'll learn about different data store types and also discover how to connect data stores to agents and add personalization for enhanced responses. Finally, you'll gain insights into common search configurations and troubleshooting techniques.
This course explores the quality assurance best practices and the tools available in Conversational Agents to ensure production grade quality during Conversational Agent development, as well as the key tenets for the creation of a robust end to end deployment lifecycle. Please note Dialogflow CX was recently renamed to Conversational Agents, Virtual agent renamed to Conversational agent, and CCAI Insights were renamed to Conversational Insights, and this course is in the process of being updated to reflect the new product names for Dialogflow CX, and Virtual Agent, CCAI Insights.
This course explores the fundamentals of the feedback loop process for Conversational Agent development and introduces the native capabilities within Conversational Agents that support it. You will also learn about advanced methods and tools to monitor the performance of your Conversational agent in Conversational Agents.
In this course, you will learn the important role that different types of webhooks play in Conversational Agents development, and how to effectively integrate them into your routine configuration of a Conversational Agent. Please note Dialogflow CX was recently renamed to Conversational Agents, Virtual agent renamed to Conversational agent, and CCAI Insights were renamed to Conversational Insights, and this course is in the process of being updated to reflect the new product names for Dialogflow CX, and Virtual Agent, CCAI Insights.
This course explores the foundational principles of conversation design to craft engaging and effective experiences that emulate human-like experiences specific to the Chat channel. Please note Dialogflow CX was recently renamed to Conversational Agents, Virtual agent renamed to Conversational agent, and CCAI Insights were renamed to Conversational Insights, and this course is in the process of being updated to reflect the new product names for Dialogflow CX, and Virtual Agent, CCAI Insights.
Discover flows in Conversational Agents and learn how to build deterministic chat and voice experiences with language models. Explore key concepts like drivers, intents, and entities, and how to use them to create conversational agents.
This course explores the best practices, methods and tools to programmatically lead CCAI virtual agent delivery. It includes a high level overview of the end to end journey for building and deploying a virtual agent, as well as the core tenets to create a strong delivery culture. Additionally, this course covers the best practices for workflow management, defect tracking, release management and post-release support to ensure optimal virtual agent performance.
This course explores using enterprise design patterns to build scalable, reliable, and secure agents within CX Agent Studio. Additionally, it covers navigating the complete development lifecycle by deploying multi-layered application security and locking down cloud infrastructure perimeters. It details the core pillars of multi-turn session persistence and real-time audio supervision to facilitate safe, continuous conversational experiences.
This is an introductory course to all solutions in the Conversational AI portfolio and the Gen AI features that are available to transform them. The course also explores the business case around Conversational AI, and the use cases and user personas addressed by the solution. Please note Dialogflow CX was recently renamed to Conversational Agents and this course is in the process of being updated to reflect the new product name for Dialogflow CX.
Migration from Oracle to Cloud Spanner using HarbourBridge. This course describes an example scenario that uses sample data during the migration. This process includes using HarbourBridge for Assessment, Schema Conversion, Schema Transformation, Data Migration, and supporting tools for data validation.
Muchas empresas tradicionales usan apps y sistemas heredados que no pueden adecuarse a las expectativas de los clientes actuales. A menudo los líderes empresariales deben elegir entre mantener sus sistemas de TI anticuados o invertir en nuevos productos y servicios. En este curso, se exploran estos desafíos y se ofrecen soluciones para superarlos con la tecnología de la nube. Como parte de la ruta de aprendizaje de Cloud Digital Leader, el objetivo de este curso es ayudar a las personas a crecer en su rol y desarrollar el futuro de su empresa.
This course discusses the key elements of Google's Data Warehouse solution portfolio and strategy.
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.
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.
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.
En este curso, se presenta Vertex AI Studio, una herramienta para interactuar con modelos de IA generativa, crear prototipos de ideas de negocio y llevarlas a producción. A través de un caso de uso envolvente, lecciones atractivas y un lab práctico, explorarás el ciclo de vida desde la instrucción hasta el producto y aprenderás cómo aprovechar Vertex AI Studio para aplicaciones multimodales de Gemini, diseño de instrucciones, ingeniería de instrucciones y ajuste de modelos. El objetivo es permitirte desbloquear el potencial de la IA generativa en tus proyectos con Vertex AI Studio.
En este curso, se te enseña a crear un modelo de generación de leyendas de imágenes con el aprendizaje profundo. Aprenderás sobre los distintos componentes de los modelos de generación de leyendas de imágenes, como el codificador y el decodificador, y cómo entrenar y evaluar tu modelo. Al final del curso, podrás crear tus propios modelos y usarlos para generar leyendas de imágenes.
En este curso, se presentan la arquitectura de transformadores y el modelo de Bidirectional Encoder Representations from Transformers (BERT). Aprenderás sobre los componentes principales de la arquitectura de transformadores, como el mecanismo de autoatención, y cómo se usa para crear el modelo BERT. También aprenderás sobre las diferentes tareas para las que puede usarse BERT, como la clasificación de texto, la respuesta de preguntas y la inferencia de lenguaje natural. Tardarás aproximadamente 45 minutos en completar este curso.
En este curso, se brinda un resumen de la arquitectura de codificador-decodificador, una arquitectura de aprendizaje automático importante y potente para realizar tareas de secuencia por secuencia, como las de traducción automática, resúmenes de texto y respuestas a preguntas. Aprenderás sobre los componentes principales de la arquitectura de codificador-decodificador y cómo entrenar y entregar estos modelos. En la explicación del lab, programarás una implementación sencilla de la arquitectura de codificador-decodificador en TensorFlow para generar poemas desde un comienzo.
Este curso es una introducción al mecanismo de atención, una potente técnica que permite a las redes neuronales enfocarse en partes específicas de una secuencia de entrada. Sabrás cómo funciona la atención y cómo puede utilizarse para mejorar el rendimiento de diversas tareas de aprendizaje automático, como la traducción automática, el resumen de textos y la respuesta a preguntas.
En este curso, se presenta una introducción a los modelos de difusión: una familia de modelos de aprendizaje automático que demostraron ser muy prometedores en el área de la generación de imágenes. Los modelos de difusión se inspiran en la física, específicamente, en la termodinámica. En los últimos años, los modelos de difusión se han vuelto populares tanto en investigaciones como en la industria. Los modelos de difusión respaldan muchos de los modelos de generación de imágenes y herramientas vanguardistas de Google Cloud. En este curso, se presenta la teoría detrás de los modelos de difusión y cómo entrenarlos y, luego, implementarlos en Vertex AI.
A medida que aumenta el uso empresarial de la inteligencia artificial y el aprendizaje automático, también crece la importancia de implementarlo responsablemente. El desafío para muchas personas es que hablar sobre la IA responsable puede ser más fácil que aplicarla. Si te interesa aprender cómo poner en funcionamiento la IA responsable en tu organización, este curso es para ti. En este curso, aprenderás cómo Google Cloud aplica estos principios en la actualidad, junto con las prácticas recomendadas y las lecciones aprendidas, para usarlos como marco de trabajo de modo que puedas crear tu propio enfoque de IA responsable.
Completa los cursos Introduction to Generative AI, Introduction to Large Language Models e Introduction to Responsible AI para obtener una insignia de habilidad. Aprueba el cuestionario final para demostrar que entiendes los conceptos básicos sobre la IA generativa. Una insignia de habilidad es una insignia digital que emite Google Cloud en reconocimiento de tu dominio de los productos y servicios de la plataforma. Para compartir tu insignia de habilidad, establece tu perfil como público y agrega la insignia a tu perfil de redes sociales.
Este es un curso introductorio de microaprendizaje destinado a explicar qué es la IA responsable, por qué es importante y cómo la implementa Google en sus productos. También se presentan los 7 principios de la IA de Google.
El curso Explorador de la IA generativa - Agent Platform es una colección de labs sobre cómo usar la IA generativa en Google Cloud. A través de los labs, aprenderás a usar los modelos de Gemini en Agent Platform. También aprenderás sobre el diseño de instrucciones, las prácticas recomendadas y cómo se puede usar para la generación de ideas, la clasificación, la extracción y el resumen de texto, y mucho más. También aprenderás a ajustar un modelo de base entrenándolo a través de un entrenamiento personalizado en Agent Platform y, luego, implementándolo en un extremo de Agent Platform.
Este es un curso introductorio de microaprendizaje en el que se explora qué son los modelos de lenguaje grandes (LLM), sus casos de uso y cómo se puede utilizar el ajuste de instrucciones para mejorar el rendimiento de los LLM. También abarca las herramientas de Google para ayudarte a desarrollar tus propias aplicaciones de IA generativa.
Este es un curso introductorio de microaprendizaje destinado a explicar qué es la IA generativa, cómo se utiliza y en qué se diferencia de los métodos de aprendizaje automático tradicionales. También menciona las herramientas de Google para ayudarte a desarrollar tus propias aplicaciones de IA generativa.
Welcome to "CCAI Conversational Design Fundamentals", the first course in the "Customer Experiences with Contact Center AI" series. In this course, learn how to design customer conversational solutions using Contact Center Artificial Intelligence (CCAI). You will be introduced to CCAI and its three pillars (Dialogflow, Agent Assist, and Insights), and the concepts behind conversational experiences and how the study of them influences the design of your virtual agent. After taking this course you will be prepared to take your virtual agent design to the next level of intelligent conversation.
Welcome to "Virtual Agent Development in Dialogflow CX for Software Devs", the third course in the "Customer Experiences with Contact Center AI" series. In this course, learn how to develop more customized customer conversational solutions using Contact Center Artificial Intelligence (CCAI). In this course, you'll be introduced to more advanced and customized handling for virtual agent conversations that need to look up and convey dynamic data, and methods available to you for testing your virtual agent and logs which can be useful for understanding issues that arise. This is an intermediate course, intended for learners with the following type of role: Software developers: Codes computer software in a programming language (e.g., C++, Python, Javascript) and often using an SDK/API.
Learn how to design, develop, and deploy customer conversational solutions using Contact Center Artificial Intelligence (CCAI). You'll also learn some best practices for integrating conversational solutions with your existing contact center software, establishing a framework for human agent assistance, and implementing solutions securely and at scale.