2.4 Describe How Google Cloud Empowers Developers to Build with AI. GENERATIVE-AI-LEADER Practice Questions (Page 1)

Questions 1–5

1. 1expert · hard

   A company wants to build an AI-powered application that uses a foundation model to generate responses and also needs to integrate with their internal APIs to perform actions. They have a development team that can write code but wants to use managed services to reduce operational overhead. They also want to be able to experiment with different foundation models before choosing one. Which approach best meets these needs?

   • AUse RAG APIs to build the application from scratch
   • BUse Agent Platform AutoML to train a custom model
   • CUse Agent Platform to build a custom agent, using Model Garden to select the foundation model
   • DUse Agent Search with prebuilt RAG
   Reveal Solution Discussion Select an answer first
2. 2foundation · easy

   What is a key business value of using RAG APIs?

   • AReplacing the need for human oversight in all AI applications
   • BGuaranteeing that all responses are 100% accurate
   • CEliminating the need for any data storage or indexing
   • DReducing development effort by providing ready-to-use components for retrieval and generation
   Reveal Solution Discussion Select an answer first
4. 3foundation · easy

   What is the primary function of Model Garden in Google Cloud?

   • ATo provide a platform for building and deploying conversational agents
   • BTo store and version large datasets used for machine learning
   • CTo offer a managed service for training custom models using AutoML
   • DTo provide a curated collection of foundation models that developers can discover, experiment with, and deploy
   Reveal Solution Discussion Select an answer first
5. 4foundation · easy

   What is the primary purpose of Agent Platform on Google Cloud?

   • ATo provide a managed environment for building, deploying, and scaling AI-powered applications and agents
   • BTo offer a repository of pre-trained models that can be downloaded and run locally on any hardware
   • CTo enable developers to create and manage virtual machines for running AI workloads
   • DTo provide a suite of data analytics tools for processing large datasets in batch
   Reveal Solution Discussion Select an answer first
6. 5expert · hard

   A company wants to build a custom model to predict customer churn from their CRM data. They have a small data science team that can write code, but they want to reduce the time spent on feature engineering and model tuning. They also want to compare the custom model's performance against a foundation model. Which approach best meets these needs?

   • AUse RAG APIs to build the churn model
   • BUse Model Garden to fine-tune a foundation model for churn prediction
   • CUse Agent Platform AutoML to build the custom model, and use Model Garden to evaluate a foundation model for comparison
   • DUse Agent Search to index CRM data and predict churn
   Reveal Solution Discussion Select an answer first