CoursesFree Quizzes
DatabricksKnowledge Retrieval and Genie Configuration

Genie & Semantic Metadata — Databricks Context Associate Practice Question

A representative Databricks Certified Context Engineer Associate (Databricks Context Associate) exam question on Genie & Semantic Metadata. Work through it below, then read why each option is right or wrong.

This question is part of the free Databricks Certified Context Engineer Associate practice test.

Short answer

The correct answer is C. In Unity Catalog table descriptions, column descriptions, and tags that are visible to Genie during space configuration..

Genie spaces leverage Unity Catalog's semantic layer, including table and column descriptions and tags. These metadata elements are the primary way to communicate business context to Genie. is incorrect because Genie does not require a separate JSON schema upload. is wrong because MLflow Model Registry is not the semantic metadata source for Genie spaces. is false because custom prompts do not override table metadata; metadata is the foundation. Proper use of Unity Catalog descriptions is the standard, documented approach.

The Question

You are setting up a Databricks Genie space for a data analytics team. The team wants Genie to understand the business context of their tables—for example, that 'revenue' is measured in USD and 'customer_segment' refers to predefined categories. Where should you define this semantic metadata to ensure Genie uses it during query generation?

AIn a separate MLflow Model Registry metadata store that must be manually linked to the Genie space.
BIn the Genie space's custom prompt engineering interface, which overrides all table metadata.
CIn Unity Catalog table descriptions, column descriptions, and tags that are visible to Genie during space configuration.Correct
DIn the Genie space settings panel under 'Semantic Configuration' by uploading a JSON schema file.

Why C is correct

Genie spaces leverage Unity Catalog's semantic layer, including table and column descriptions and tags. These metadata elements are the primary way to communicate business context to Genie. is incorrect because Genie does not require a separate JSON schema upload. is wrong because MLflow Model Registry is not the semantic metadata source for Genie spaces. is false because custom prompts do not override table metadata; metadata is the foundation. Proper use of Unity Catalog descriptions is the standard, documented approach.

Why the other options are wrong

Option A: In a separate MLflow Model Registry metadata store that must be manually linked to the Genie space.

Option A does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (C) is the only one that fully meets every constraint stated in the question.

Option B: In the Genie space's custom prompt engineering interface, which overrides all table metadata.

Option B does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (C) is the only one that fully meets every constraint stated in the question.

Option D: In the Genie space settings panel under 'Semantic Configuration' by uploading a JSON schema file.

Option D does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (C) is the only one that fully meets every constraint stated in the question.

Key idea: Genie & Semantic Metadata

Genie spaces leverage Unity Catalog's semantic layer, including table and column descriptions and tags. These metadata elements are the primary way to communicate business context to Genie. is incorrect because Genie does not require a separate JSON schema upload. is wrong because MLflow Model Registry is not the semantic metadata source for Genie spaces. is false because custom prompts do not override table metadata; metadata is the foundation. Proper use of Unity Catalog descriptions is the standard, documented approach. On the Databricks Context Associate exam, questions in the "Knowledge Retrieval and Genie Configuration" domain test whether you can map a scenario's constraints to the right choice. Read the requirement carefully, eliminate options that violate any single constraint, and pick the one that satisfies all of them with the least operational overhead.

Ready to see how you'd score?

Take the free practice quiz and find out which Databricks Certified Context Engineer Associate domains you need to focus on. No signup required.

Take the free quizSee all 215+ practice questions

Practice 5 similar questions

Same cert, same or adjacent domain. Use these after reviewing the explanation.

1Mlflow & Evaluation — Databricks Context Associate Practice QuestionFoundations of Context Engineering2Instruction Testing & Vector Search — Databricks Context Associate Practice QuestionSystem Prompt and Instruction Design3Memory Architecture & Canary Deployment — Databricks Context Associate Practice QuestionMemory Architecture with Lakebase and MLflow4Tool Design & Least Privilege — Databricks Context Associate Practice QuestionTool Design, MCP, and Agent Context5Choose Retrieval Strategy & Permitting — Databricks Context Associate Practice QuestionContext Compression and Compaction

Related Databricks Certified Context Engineer Associate Practice Questions

Mlflow & Evaluation — Databricks Context Associate Practice Question→Instruction Testing & Vector Search — Databricks Context Associate Practice Question→Memory Architecture & Canary Deployment — Databricks Context Associate Practice Question→

Official sources used

Verify program and exam details at the source before scheduling.

docs.databricks.comEN: Agents