2.4 Describe How Google Cloud Empowers Developers to Build with AI. GENERATIVE-AI-LEADER Practice Questions (Page 3)

Questions 11–15

1. 11expert · hard

   A company needs to build a custom model to classify customer feedback into sentiment categories. They have a small dataset and limited ML expertise. They tried using a foundation model from Model Garden but found it too generic for their domain. They need a model tailored to their data without writing ML code. What should they do?

   • AUse Agent Platform AutoML to train a custom model on their labeled feedback data
   • BFine-tune a foundation model from Model Garden using custom code
   • CUse RAG APIs to augment the feedback with external data
   • DUse Agent Search to index the feedback and generate sentiment labels
   Reveal Solution Discussion Select an answer first
2. 12application · medium

   A software company wants to add retrieval-augmented generation to its existing customer-facing application. They have a development team that can write code and want to integrate RAG directly into their app's backend. What should they use?

   • AAgent Search with prebuilt RAG
   • BAgent Platform AutoML
   • CRAG APIs
   • DModel Garden to select a model
   Reveal Solution Discussion Select an answer first
4. 13foundation · easy

   What is the primary purpose of Agent Platform AutoML?

   • ATo enable developers to build custom machine learning models without needing extensive ML expertise
   • BTo provide a repository of pre-trained foundation models for immediate use
   • CTo provide a platform for building conversational agents
   • DTo manage the deployment of models to mobile devices
   Reveal Solution Discussion Select an answer first
5. 14application · medium

   A financial services company wants to build a custom AI agent that can look up account information, answer customer questions, and escalate complex issues to human agents. They need to integrate the agent with their existing CRM and ticketing systems. What should they use?

   • AAgent Platform to build a custom agent with tools and workflows
   • BRAG APIs only
   • CAgent Platform AutoML
   • DAgent Search alone
   Reveal Solution Discussion Select an answer first
6. 15foundation · easy

   What is the primary function of Google Cloud's RAG APIs?

   • ATo allow developers to integrate retrieval-augmented generation into their applications
   • BTo store and query large datasets
   • CTo provide a pre-trained model for image generation
   • DTo manage the lifecycle of virtual machines
   Reveal Solution Discussion Select an answer first