A Generative AI Engineer is deploying an agent using Mosaic AI Model Serving. The agent needs to access various Databricks resources, including Vector Search, Databricks SQL, and Functions. They need to find the easiest and best-practice way to authenticate the deployed agent to access these resources.
What approach should they choose?

• A. Log the authentication token while logging the agent; this token will be automatically used for authentication.
• B. Set appropriate permissions on the Model Serving endpoint for the agent, as these permissions will be used when connecting to other resources.
• C. Embed authentication credentials within the agent's code to access the required resources.
• D. Define resource dependencies while logging the agent and deploy it with the Agent Framework.

A team uses Mosaic AI Vector Search to retrieve documents for their Retrieval-Augmented Generation (RAG) pipeline. The search query returns five relevant documents, and the first three are added to the prompt as context. Performance evaluation with Agent Evaluation shows that some lower-ranked retrieved documents have higher context relevancy scores than higher-ranked documents. Which option should the team consider to optimize this workflow?

• A. Use a different embedding model for computing document embeddings.
• B. Increase the number of documents added to the prompt to improve context relevance.
• C. Use a reranker to order the documents based on the relevance scores.
• D. Modify the prompt to instruct the LLM to order the documents based on the relevance scores.

A Generative Al Engineer is creating an LLM-based application. The documents for its retriever have been chunked to a maximum of 512 tokens each. The Generative Al Engineer knows that cost and latency are more important than quality for this application. They have several context length levels to choose from.
Which will fulfill their need?

• A. context length 512: smallest model is 0.13GB and embedding dimension 384
• B. context length 2048: smallest model is 11GB and embedding dimension 2560
• C. context length 32768: smallest model is 14GB and embedding dimension 4096
• D. context length 514; smallest model is 0.44GB and embedding dimension 768

A Generative Al Engineer is responsible for developing a chatbot to enable their company's internal HelpDesk Call Center team to more quickly find related tickets and provide resolution. While creating the GenAI application work breakdown tasks for this project, they realize they need to start planning which data sources (either Unity Catalog volume or Delta table) they could choose for this application. They have collected several candidate data sources for consideration:
call_rep_history: a Delta table with primary keys representative_id, call_id. This table is maintained to calculate representatives' call resolution from fields call_duration and call start_time.
transcript Volume: a Unity Catalog Volume of all recordings as a *.wav files, but also a text transcript as *.txt files.
call_cust_history: a Delta table with primary keys customer_id, cal1_id. This table is maintained to calculate how much internal customers use the HelpDesk to make sure that the charge back model is consistent with actual service use.
call_detail: a Delta table that includes a snapshot of all call details updated hourly. It includes root_cause and resolution fields, but those fields may be empty for calls that are still active.
maintenance_schedule - a Delta table that includes a listing of both HelpDesk application outages as well as planned upcoming maintenance downtimes.
They need sources that could add context to best identify ticket root cause and resolution.
Which TWO sources do that? (Choose two.)

• A. call_detail
• B. maintenance_schedule
• C. call_cust_history
• D. call_rep_history
• E. transcript Volume

A Generative AI Engineer at an automotive company would like to build a question-answering chatbot to help customers answer specific questions about their vehicles. They have:
* A catalog with hundreds of thousands of cars manufactured since the 1960s
* Historical searches with user queries and successful matches
* Descriptions of their own cars in multiple languages
They have already selected an open-source LLM and created a test set of user queries. They need to discard techniques that will not help them build the chatbot. Which do they discard?

• A. Adding few-shot examples for response generation
• B. Setting chunk size to match the model ' s context window to maximize coverage
• C. Fine-tuning an embedding model on automotive terminology
• D. Implementing metadata filtering based on car models and years