Generative AI Leader Fundamentals of Generative AI Practice Question
A media company wants to generate personalized video summaries for users based on their viewing history. They plan to use a generative AI model on Vertex AI. Which technique should they use to ensure the summaries are tailored to each user's preferences?
⚠ Common exam trap
The trap here is assuming that fine-tuning is necessary for personalization, when RAG can achieve it more efficiently by retrieving user-specific context.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Retrieval-augmented generation (RAG) with a vector database of user viewing history and video metadata.
Retrieval-augmented generation (RAG) with a vector database allows the system to fetch relevant user-specific data, such as past viewing history and video metadata, and use it to condition the model's output. This results in summaries tailored to each user's preferences. Fine-tuning per user is unscalable, and generic prompts or temperature adjustments do not provide true personalization.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use a high temperature setting to generate diverse summaries that might match user preferences.
Why it's wrong here
High temperature increases randomness but does not personalize outputs to a specific user. It may produce varied summaries, but they are not tailored based on viewing history. Personalization requires user-specific context, which temperature alone cannot provide.
- ✗
Apply prompt engineering with a generic template that asks for a summary in a friendly tone.
Why it's wrong here
A generic prompt template does not incorporate individual user data, so the summaries would not be personalized. While tone can be adjusted, the content would not reflect each user's viewing history. Personalization demands user-specific input, such as retrieved history.
- ✗
Fine-tune a separate model for each user on their viewing history.
Why it's wrong here
Fine-tuning a model per user is impractical due to computational cost and data requirements. It would not scale for a media company with many users. RAG provides personalization more efficiently by retrieving relevant context at inference time.
- ✓
Retrieval-augmented generation (RAG) with a vector database of user viewing history and video metadata.
Why this is correct
RAG retrieves relevant context from a vector database based on the user's viewing history, then passes it to the model to generate personalized summaries. This ensures each summary reflects the user's preferences by incorporating their past behavior. It is a powerful technique for personalization without fine-tuning per user.
Go deeper
Related to this question
About these practice questions
Courseiva writes every Generative AI Leader question from scratch — 1,008 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
This Generative AI Leader practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Generative AI Leader exam.