Total Articles: 10
This codelab guides you through building an itinerary planning agent using the Agent Development Kit (ADK) and Google Maps Grounding. It covers setting up the development environment, defining tools, creating an agent, and testing the agent with sample queries. This is aimed at developers interested in building intelligent agents.
This codelab guides you through building a multi-agent system using the Gemini and Gemma models. You'll learn how to design and implement a system where multiple AI agents collaborate to solve complex tasks. This is ideal for developers interested in exploring advanced AI concepts and practical applications of large language models.
This codelab explores frontend experiences using the ADK (Assistant Development Kit) and A2UI (Actions on Google User Interface). It focuses on building interactive and engaging interfaces for Google Assistant applications. The codelab guides users through the process of designing and implementing voice-based and visual components, enabling them to create rich, multimodal experiences for users interacting with Google Assistant.
This codelab guides you through building an ADK agent, emphasizing the integration of skills and tools. It explores how to enhance agents with capabilities that allow them to interact effectively with various services and data sources. The codelab focuses on practical implementation and real-world application of agent development concepts.
This codelab guides you through using Gemini Data Analytics to query and analyze data stored in AlloyDB. You'll learn how to connect to your database, explore the data, and generate insights using natural language queries. This lab is designed for data analysts, database administrators, and anyone interested in leveraging AI to simplify data exploration.
This codelab explores using AI agents to rapidly forecast from raw data. It focuses on leveraging large language models and other AI tools to automate and accelerate the forecasting process, enabling quick insights from data for various applications. The content is geared towards developers and data scientists interested in applying AI to time series analysis and prediction.
This codelab guides you through building a secure agent that protects access and data. It covers key aspects of secure agent design, including authentication, authorization, and data encryption. The content is tailored for developers and security engineers interested in implementing robust security measures in their applications and systems.
This codelab guides you through building a real-time fraud detection system using Google Cloud Spanner and BigQuery. It focuses on leveraging Spanner's low-latency transactions and BigQuery's analytical capabilities to identify and respond to fraudulent activities in real time. This lab is targeted toward data engineers, database administrators, and developers interested in building scalable and robust fraud detection systems.
This codelab guides you through deploying and scaling a stateful data science agent using Agent Engine. It focuses on practical implementation, covering setting up the environment, deploying the agent, and scaling resources to handle increased workloads, making it ideal for data scientists and engineers.
This codelab guides you through deploying a sample application to Cloud Run, covering essential aspects such as containerization, continuous integration/continuous deployment (CI/CD), and traffic management. It is designed to provide a comprehensive understanding of how to leverage Cloud Run for deploying scalable and reliable applications.