Pass Databricks-Generative-AI-Engineer-Associate Exam Guide

For a small, cost-conscious startup in the cancer research field, choosing a domain-specific and smaller LLM is the most effective strategy. Here ' s why B is the best choice:

Domain-specific performance : A smaller LLM that has been fine-tuned for the domain of cancer research will outperform a general-purpose LLM for specialized queries. This ensures high-quality responses without needing to rely on a large, expensive LLM.

Cost-efficiency : Smaller models are cheaper to run, both in terms of compute resources and API usage costs. A domain-specific smaller LLM can deliver good quality responses without the need for the extensive computational power required by larger models.

Focused knowledge : In a specialized field like cancer research, having an LLM tailored to the subject matter provides better relevance and accuracy for queries, while keeping costs low. Large, general-purpose LLMs may provide irrelevant information, leading to inefficiency and higher costs.

This approach allows the startup to balance quality, cost, and customer satisfaction effectively, making it the most suitable strategy.

The Multi-Agent Supervisor is designed to coordinate specialized agents and tools behind a unified entry point. It interprets the incoming request, selects suitable capabilities, delegates work, and combines results when necessary. In this scenario, document questions can be handled by a knowledge-retrieval specialist, while event-code extraction can be assigned to a specialized extraction capability. The supervisor provides the coordination needed to select between those tasks and handle requests requiring multiple steps. A Knowledge Assistant’s conversational interface does not itself make it the appropriate general-purpose orchestrator. Adding vector indexes also does not establish specialized extraction and routing behavior. Although option A names the same component, its justification misses the central requirement: coordinated delegation across distinct capabilities. Databricks documentation

Model inversion attacks occur when an attacker uses the model ' s outputs to reconstruct the sensitive training data used during the fine-tuning process. To mitigate this in a public-facing application, implementing AI Guardrails is the most relevant strategy. Guardrails act as a programmable " filter " between the LLM and the end-user. They can be configured to detect if a model ' s response contains patterns that look like proprietary training data or PII (Personally Identifiable Information). While ACLs (B) and ABAC (D) protect the model ' s infrastructure (who can invoke the API), they do not inspect the content of the output, which is where the inversion attack actually manifests. Databricks provides integrated guardrail capabilities (via Mosaic AI Gateway) specifically to enforce compliance and prevent the leakage of sensitive internal knowledge that may have been baked into the model weights during fine-tuning.

A scheduled SQL query using ai_query() is a straightforward way to process text already stored in a Delta table. The query can send each post to a supported model with instructions to return a summary and sentiment, then persist the results for internal reporting. A pay-per-token service avoids dedicating serving capacity to a workload containing only a few hundred daily records. Calling an external batch API introduces additional integration and result-handling work, while downloading and hosting a model adds infrastructure responsibilities. Provisioned throughput is generally more appropriate when sustained demand justifies dedicated capacity. B is the best fit among these choices; actual costs still depend on model selection, token volume, SQL compute, and the applicable inference pricing. Databricks documentation