Home / GenAI Engineer practice test / Design Applications / Question

Databricks Generative AI Engineer Associate · free practice question

A manufacturing firm's business intelligence department aims to empower 200 non-technical staff members to effortlessly query their Databricks Delta Lake…

Exam-style question on Design Applications from the free GenAI Engineer practice test, with the answer and a full explanation below.

Updated November 11, 2026

Design Applications

A manufacturing firm's business intelligence department aims to empower 200 non-technical staff members to effortlessly query their Databricks Delta Lake datasets (including production metrics, inventory levels, and regional sales figures) using everyday language. Users should be able to input questions like 'Show me the top 5 lowest-performing product categories by revenue last quarter?' and instantly receive precise, data-backed responses — without having to write SQL code, submit a data team request, or engage in bespoke agent creation. Crucially, Unity Catalog access policies must be automatically enforced. Considering Databricks Agent Bricks functionalities, which solution best fits this operational requirement?

  1. AKnowledge Assistant, with the Delta table schemas uploaded as PDF documents so the chatbot answers business questions from those schema descriptions
  2. BInformation Extraction, configured to scan the Delta tables on a schedule and extract key performance indicators into a summary table users can read
  3. CSupervisor Agent, routing each question to a production, inventory or sales sub-agent that generates custom SQL for its own domain
  4. DAI/BI Genie, with a Genie space over the Unity Catalog tables that turns natural language questions into SQL and runs it under each user's permissions
  5. ECustom LLM, fine-tuned on historical SQL query logs and Delta table schemas so the model produces SQL for new questions without extra tools
Answer & explanation

Correct answer: D

WHY D is correct: AI/BI Genie is the Databricks Agent Brick specifically designed to 'turn your tables into an expert AI chatbot.' It takes Delta Lake tables registered in Unity Catalog as its data source, interprets natural language questions, generates SQL, executes it against the live data, and returns grounded answers — precisely the use case described. Unity Catalog access controls are applied automatically because Genie operates within the Unity Catalog governance framework, ensuring each user only sees data they are authorized to access. This requires zero custom agent development and is designed for non-technical users.

WHY NOT A: Knowledge Assistant is designed for document-based Q&A (PDF, text files, unstructured content). Uploading schema documents does not give the chatbot access to the actual data in the Delta tables — it can only answer schema-level questions ('What columns does the sales table have?'), not data-level questions ('What were the top 5 underperforming product lines?'). Knowledge Assistant cannot execute SQL or query live tables.

WHY NOT B: Information Extraction is designed to transform unstructured documents (invoices, emails, contracts) into structured fields — not to query existing structured Delta tables. Pre-extracting KPIs into a summary table requires knowing in advance every question users might ask, which is impossible and defeats the purpose of a natural language interface.

WHY NOT C: Building a Supervisor Agent with domain-specific sub-agents that write custom SQL requires significant engineering effort per sub-agent, custom SQL logic maintenance, and periodic updates as schemas evolve. This contradicts the 'without custom agent development' requirement. Genie provides this capability out of the box.

WHY NOT E: Fine-tuning a Custom LLM bakes knowledge of the table schemas into the model weights at training time. This approach cannot access live data (fine-tuned weights do not execute SQL), requires periodic retraining as schemas change, and produces stale answers. It is inappropriate for real-time tabular data querying.

Take the full GenAI Engineer practice test free →

Would you pass today?

This question is one of 45 in the free, timed Databricks Generative AI Engineer Associate practice test. Take it and get a section-by-section score.

Start the free test →