Databricks Certified Generative AI Engineer Associate practice questions
10 questions in 1 test. Open one to answer it on its own, or take a whole test.
Test 1
Take Test 1 ›- An HR team keeps several hundred policy PDFs in a Unity Catalog volume. They want a chatbot that employees can ask questions such as "How many days of parental leave do I get?"… · Design Applications
- A RAG application over long engineering manuals splits each manual into 2,000-token chunks with no overlap. The chunks are embedded by a model whose maximum input length is 512… · Data Preparation
- An engineer writes chunked documents to a Delta table in Unity Catalog. They then try to create a Delta Sync index with Databricks-managed embeddings on a standard Databricks AI… · Data Preparation
- Users of an internal benefits RAG assistant report that it confidently gives outdated reimbursement limits. The team runs mlflow.genai.evaluate() on 200 labeled questions: -… · Application Development
- A support agent for an industrial parts distributor retrieves from a Databricks AI Search (formerly Vector Search) index of product descriptions. Customer queries mix natural… · Application Development
- A team changes its agent's system prompt several times a week. Right now the prompt is a string in the agent code, so every wording change needs a full code redeploy, and there… · Assembling and Deploying Applications
- Each night, about 5 million new support tickets land in a Unity Catalog Delta table. A SQL-focused analytics team needs every ticket labeled with a category and a sentiment using… · Assembling and Deploying Applications
- An agent retrieves from an AI Search index, calls a Unity Catalog function as a tool, and calls a Foundation Model APIs endpoint. It works when run interactively in a notebook… · Assembling and Deploying Applications
- A customer-facing chat app calls a Foundation Model APIs pay-per-token endpoint in non-streaming mode. Customers sometimes paste credit card numbers into their messages… · Governance
- Before a release, a team builds an evaluation dataset of 300 real user questions from its production traces. The dataset has the inputs, the agent's outputs, and the retrieved… · Evaluation and Monitoring