2.4 Describe How Google Cloud Empowers Developers to Build with AI. GENERATIVE-AI-LEADER Practice Questions (Page 2)

Questions 6–10

1. 6foundation · easy

   What is a key business value of building custom agents with Agent Platform?

   • AEliminating the need for any human involvement in customer interactions
   • BReducing the need for data security and access controls
   • CGuaranteeing that the agent will never make a mistake
   • DCreating agents that are tailored to specific business processes and data
   Reveal Solution Discussion Select an answer first
2. 7application · medium

   A retail company wants to build a customer-support chatbot that answers questions from its product catalog and returns grounded responses with citations. The team has limited ML expertise and wants to use Google Cloud's managed services. Which combination of services should they use?

   • AAgent Platform with Agent Search for prebuilt RAG
   • BAgent Platform AutoML to train a custom classification model
   • CVertex AI custom training with a text generation model
   • DAgent Search alone with a simple web interface
   Reveal Solution Discussion Select an answer first
4. 8application · medium

   A data science team wants to compare several foundation models for a sentiment-analysis task. They need to quickly test different models with the same prompt and then deploy the best one to an endpoint. Which Google Cloud capability best supports this workflow?

   • AAgent Search to index the sentiment data and generate responses
   • BModel Garden for discovery and experimentation, then deploy via Agent Platform
   • CRAG APIs to build a retrieval pipeline for the models
   • DAgent Platform AutoML to train a custom model from scratch
   Reveal Solution Discussion Select an answer first
5. 9expert · hard

   A company wants to build a chatbot that answers questions from a large knowledge base. They need the answers to be grounded in the knowledge base to avoid hallucinations. They have a development team that can write code, but they want to minimize the amount of custom ML infrastructure they need to maintain. Which approach should they take?

   • AUse Agent Search with prebuilt RAG
   • BUse Agent Platform AutoML to train a model on the knowledge base
   • CUse Model Garden to select a model and fine-tune it on the knowledge base
   • DUse RAG APIs to build a custom RAG pipeline
   Reveal Solution Discussion Select an answer first
6. 10expert · hard

   A company wants to improve employee productivity by providing a conversational search tool that can answer questions from internal documents and also allow employees to perform actions like booking meeting rooms. They have a development team but want to minimize custom ML work. They need answers to be grounded in the documents. Which approach best meets these requirements?

   • AUse Agent Search alone for both search and room booking
   • BUse Agent Platform AutoML to train a model for both tasks
   • CBuild a custom agent on Agent Platform, using Agent Search with prebuilt RAG for grounded answers and a tool for room booking
   • DUse RAG APIs to build a custom solution
   Reveal Solution Discussion Select an answer first