You’ve built agents with advanced configuration—now give them real-world capabilities. Equip agents with tools that enable searching the web, executing code, querying databases, and performing custom actions. Transform agents from intelligent responders into capable assistants that take action.
Explore AI-powered search technologies, tools, and applications in this course. Learn semantic search utilizing vector embeddings, hybrid search combining semantic and keyword approaches, and retrieval-augmented generation (RAG) minimizing AI hallucinations as a grounded AI agent. Gain practical experience with Vertex AI Vector Search to build your intelligent search engine.
In this course, you’ll learn to use the Google Agent Development Kit to build complex, multi-agent systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You’ll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine. Please note these labs are based off a pre-released version of this product. There may be some lag on these labs as we provide maintenance updates.
Turn your understanding of agents into practical reality by building, configuring, and running your first AI agent using Google’s Agent Development Kit (ADK). In this hands-on course, you’ll set up a complete ADK development environment, create agents with both Python code and YAML configuration, and run them through multiple interfaces. You’ll also learn the core parameters that define agent behavior, taking what you learned in course 1 and applying it to working code.
AI Agents represent a major shift beyond traditional large language models (LLMs): instead of simply generating text-based solutions, they can also act autonomously to execute them. This course introduces the fundamentals of AI Agents, how they differ from LLM APIs, and where they add value in the real world. Based on Google’s agents whitepaper, it provides the theoretical foundation needed before writing your first lines of agent code—ideal for developers, architects, and technical decision-makers who want to understand AI systems through the lens of autonomous, goal-directed behavior (and not just text generation). Join the community forum for questions and discussions.
This structured course is for developers interested in building intelligent agents using the Agent Development Kit (ADK). It combines hands-on experience, core concepts, and practical application, to provide a comprehensive guide to using ADK. You can also join our community of Google Cloud experts and peers to ask questions, collaborate on answers, and connect with the Googlers making the products you use every day.
This content is deprecated. Please see the latest version of the course, here.
Complete the intermediate Develop Gen AI Apps with Gemini and Streamlit skill badge course to demonstrate skills in text generation, applying function calls with the Python SDK and Gemini API, and deploying a Streamlit application with Cloud Run. In this course, you learn Gemini prompting, test Streamlit apps in Cloud Shell, and deploy them as Docker containers in Cloud Run.
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.
Text Prompt Engineering Techniques introduces you to consider different strategic approaches & techniques to deploy when writing prompts for text-based generative AI tasks.
This course introduces Vertex AI Studio, a tool to interact with generative AI models, prototype business ideas, and launch them into production. Through an immersive use case, engaging lessons, and a hands-on lab, you’ll explore the prompt-to-product lifecycle and learn how to leverage Vertex AI Studio for Gemini multimodal applications, prompt design, prompt engineering, and model tuning. The aim is to enable you to unlock the potential of gen AI in your projects with Vertex AI Studio.
This course teaches you how to create an image captioning model by using deep learning. You learn about the different components of an image captioning model, such as the encoder and decoder, and how to train and evaluate your model. By the end of this course, you will be able to create your own image captioning models and use them to generate captions for images
This course introduces you to the Transformer architecture and the Bidirectional Encoder Representations from Transformers (BERT) model. You learn about the main components of the Transformer architecture, such as the self-attention mechanism, and how it is used to build the BERT model. You also learn about the different tasks that BERT can be used for, such as text classification, question answering, and natural language inference.This course is estimated to take approximately 45 minutes to complete.
This course gives you a synopsis of the encoder-decoder architecture, which is a powerful and prevalent machine learning architecture for sequence-to-sequence tasks such as machine translation, text summarization, and question answering. You learn about the main components of the encoder-decoder architecture and how to train and serve these models. In the corresponding lab walkthrough, you’ll code in TensorFlow a simple implementation of the encoder-decoder architecture for poetry generation from the beginning.
This course will introduce you to the attention mechanism, a powerful technique that allows neural networks to focus on specific parts of an input sequence. You will learn how attention works, and how it can be used to improve the performance of a variety of machine learning tasks, including machine translation, text summarization, and question answering. This course is estimated to take approximately 45 minutes to complete.
This course introduces diffusion models, a family of machine learning models that recently showed promise in the image generation space. Diffusion models draw inspiration from physics, specifically thermodynamics. Within the last few years, diffusion models became popular in both research and industry. Diffusion models underpin many state-of-the-art image generation models and tools on Google Cloud. This course introduces you to the theory behind diffusion models and how to train and deploy them on Vertex AI.
Im szerzej wykorzystuje się w firmach sztuczną inteligencję i systemy uczące się, tym większej wagi nabiera odpowiedzialne podejście do opracowywania tych technologii. Wielu organizacjom trudniej jest jednak wprowadzić zasady odpowiedzialnej AI w praktyce niż tylko o tym rozmawiać. To szkolenie jest przeznaczone dla osób, które chcą się dowiedzieć, jak wdrożyć odpowiedzialną AI w swojej organizacji. W jego trakcie dowiesz się, jak robimy to w Google Cloud, oraz poznasz sprawdzone metody i wnioski z naszych działań w tym zakresie. Pomoże Ci to opracować własne podejście do odpowiedzialnej AI.
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.
Celem tego szybkiego szkolenia dla początkujących jest wyjaśnienie, czym jest odpowiedzialna AI i dlaczego jest ważna, oraz przedstawienie, jak Google wprowadza ją w swoich usługach. Szkolenie zawiera także wprowadzenie do siedmiu zasad Google dotyczących sztucznej inteligencji.
To szybkie szkolenie dla początkujących wyjaśnia, czym są duże modele językowe (LLM) oraz jakie są ich zastosowania. Przedstawia również możliwości zwiększenia ich wydajności przez dostrajanie przy użyciu promptów oraz narzędzia Google, które pomogą Ci tworzyć własne aplikacje korzystające z generatywnej AI.
Celem tego szybkiego szkolenia dla początkujących jest wyjaśnienie, czym jest generatywna AI oraz jakie są jej zastosowania. Szkolenie przedstawia również różnice pomiędzy tą technologią a tradycyjnymi systemami uczącymi się, a także narzędzia Google, które pomogą Ci tworzyć własne aplikacje korzystające z generatywnej AI.
This course enables system integrators and partners to understand the principles of automated migrations, plan legacy system migrations to Google Cloud leveraging G4 Platform, and execute a trial code conversion.
This course introduces the Google Cloud big data and machine learning products and services that support the data-to-AI lifecycle. It explores the processes, challenges, and benefits of building a big data pipeline and machine learning models with Vertex AI on Google Cloud.
Ukończ szkolenie wprowadzające Przygotowywanie danych do użycia z interfejsami ML w Google Cloud, aby zdobyć odznakę potwierdzającą zdobycie następujących umiejętności: czyszczenie danych przy użyciu usługi Dataprep firmy Trifacta, uruchamianie potoków danych w Dataflow, tworzenie klastrów i uruchamianie zadań Apache Spark w Dataproc, a także wywoływanie interfejsów API dotyczących uczenia maszynowego, w tym Cloud Natural Language API, Google Cloud Speech-to-Text API oraz Video Intelligence API.
This is the first of two Quests of hands-on labs is derived from the exercises from the book Data Science on Google Cloud Platform, 2nd Edition by Valliappa Lakshmanan, published by O'Reilly Media, Inc. In this first Quest, covering up through chapter 8, you are given the opportunity to practice all aspects of ingestion, preparation, processing, querying, exploring and visualizing data sets using Google Cloud tools and services.
Aby zdobyć odznakę umiejętności, ukończ szkolenie Budowanie sieci w Google Cloud, w trakcie którego poznasz różne sposoby wdrażania i monitorowania aplikacji i dowiesz się, jak: przeglądać role uprawnień, dodawać/usuwać dostęp do projektu, tworzyć sieci VPC, wdrażać i monitorować maszyny wirtualne Compute Engine, pisać zapytania SQL oraz wdrażać aplikacje przy użyciu różnych metod w Kubernetes.
Ukończ szkolenie wprowadzające Wdrażanie równoważenia obciążenia Cloud Load Balancing w Compute Engine, aby zdobyć odznakę potwierdzającą zdobycie następujących umiejętności: tworzenie i wdrażanie maszyn wirtualnych w Compute Engine oraz konfigurowanie sieciowych systemów równoważenia obciążenia i systemów równoważenia obciążenia aplikacji.
This accelerated on-demand course introduces participants to the comprehensive and flexible infrastructure and platform services provided by Google Cloud. Through a combination of video lectures, demos, and hands-on labs, participants explore and deploy solution elements, including securely interconnecting networks, load balancing, autoscaling, infrastructure automation and managed services.
This accelerated on-demand course introduces participants to the comprehensive and flexible infrastructure and platform services provided by Google Cloud with a focus on Compute Engine. Through a combination of video lectures, demos, and hands-on labs, participants explore and deploy solution elements, including infrastructure components such as networks, systems and applications services. This course also covers deploying practical solutions including customer-supplied encryption keys, security and access management, quotas and billing, and resource monitoring.
This accelerated on-demand course introduces participants to the comprehensive and flexible infrastructure and platform services provided by Google Cloud with a focus on Compute Engine. Through a combination of video lectures, demos, and hands-on labs, participants explore and deploy solution elements, including infrastructure components such as networks, virtual machines and applications services. You will learn how to use the Google Cloud through the console and Cloud Shell. You'll also learn about the role of a cloud architect, approaches to infrastructure design, and virtual networking configuration with Virtual Private Cloud (VPC), Projects, Networks, Subnetworks, IP addresses, Routes, and Firewall rules.