A Generative Al Engineer is working with a retail company that wants to enhance its customer experience by automatically handling common customer inquiries. They are working on an LLM-powered Al solution that should improve response times while maintaining a personalized interaction. They want to define the appropriate input and LLM task to do this.
Which input/output pair will do this?

• A. Input: Customer reviews; Output Group the reviews by users and aggregate per-user average rating, then respond
• B. Input: Customer service chat logs; Output Group the chat logs by users, followed by summarizing each user ' s interactions, then respond
• C. Input: Customer reviews: Output Classify review sentiment
• D. Input: Customer service chat logs; Output: Find the answers to similar questions and respond with a summary

A Generative AI Engineer is building an interactive catalog for a company's inventory system that allows users to search for any item using a plain-text description. There are currently about 17,000 items, and new items are not frequently added. They need a solution that will be the most cost-effective and easy for the company to maintain.
Which solution should the engineer choose?

• A. Storage-optimized vector search with a Direct Vector Access index, triggered sync.
• B. Standard vector search with self-managed embeddings and a Delta Sync index, continuous sync.
• C. Standard vector search with Databricks-managed embeddings and a Delta Sync index, continuous sync.
• D. Standard vector search with Databricks-managed embeddings and a Delta Sync index, triggered sync.

A Generative Al Engineer is building a production-ready LLM system which replies directly to customers.
The solution makes use of the Foundation Model API via provisioned throughput. They are concerned that the LLM could potentially respond in a toxic or otherwise unsafe way. They also wish to perform this with the least amount of effort.
Which approach will do this?

• A. Add a regex expression on inputs and outputs to detect unsafe responses.
• B. Add some LLM calls to their chain to detect unsafe content before returning text
• C. Host Llama Guard on Foundation Model API and use it to detect unsafe responses
• D. Ask users to report unsafe responses

A Generative AI Engineer is deploying a customer-facing, fine-tuned LLM on their public website. Given the large investment the company put into fine-tuning this model, and the proprietary nature of the tuning data, they are concerned about model inversion attacks. Which of the following Databricks AI Security Framework (DASF) risk mitigation strategies are most relevant to this use case?

• A. Use secure model features with Databricks Feature Store
• B. Apply attribute-based access controls (ABAC) to limit unauthorized access
• C. Implement AI guardrails to allow users to configure and enforce compliance
• D. Leverage Databricks access control lists (ACLs) to configure permissions for accessing models

A Generative AI Engineer is designing a RAG application for answering user questions on technical regulations as they learn a new sport.
What are the steps needed to build this RAG application and deploy it?

• A. Ingest documents from a source - > Index the documents and save to Vector Search - > Evaluate model
  - > Deploy it using Model Serving
• B. Ingest documents from a source - > Index the documents and save to Vector Search - > User submits queries against an LLM - > LLM retrieves relevant documents - > LLM generates a response - > Evaluate model - > Deploy it using Model Serving
• C. User submits queries against an LLM - > Ingest documents from a source - > Index the documents and save to Vector Search - > LLM retrieves relevant documents - > LLM generates a response - > Evaluate model - > Deploy it using Model Serving
• D. Ingest documents from a source - > Index the documents and saves to Vector Search - > User submits queries against an LLM - > LLM retrieves relevant documents - > Evaluate model - > LLM generates a response - > Deploy it using Model Serving