Governance and Guardrails — Databricks Generative AI Engineer practice questions

Unity Catalog governance for AI tools provides:

1. Faster query execution against governed tables
2. Central access control, lineage, and auditing
3. Cheaper compute for jobs that read the tables
4. Higher accuracy for models registered under it

Answer: B — Central access control, lineage, and auditing

B) Correct — Unity Catalog applies one permission, lineage, and audit model across tables, models, vector indexes, and functions. A) Query speed comes from compute and layout. C) Governance does not reduce compute cost. D) Registration does not change model quality.

To demonstrate compliance, the team should retain:

1. Inference Tables, MLflow records, lineage, Gateway logs
2. Free-form engineering notes kept in a shared team drive
3. The Slack channel history where the incidents were raised
4. Verbal confirmation from the engineers who reviewed it

Answer: A — Inference Tables, MLflow records, lineage, Gateway logs

A) These four together cover requests, model provenance, asset relationships, and policy enforcement for the mandated retention period. B) Informal notes are neither complete nor tamper-evident. C) Chat history is unstructured and usually expires. D) Verbal confirmation leaves no record at all.

Granting an analyst access to query a model via SQL function should be done by:

1. Sharing the exported model file over cloud storage
2. Granting the analyst cluster administrator rights
3. Sharing the serving endpoint URL and an access token
4. Granting EXECUTE on a UC function wrapping ai_query

Answer: D — Granting EXECUTE on a UC function wrapping ai_query

D) A UC function plus an EXECUTE grant gives the analyst exactly one capability, auditable and revocable, without exposing the endpoint. A) Handing over the artifact bypasses governance entirely. B) Cluster admin is far broader than the task requires. C) A raw URL and token offer no fine-grained control or audit trail.

Which Unity Catalog privileges does an agent's identity typically need at runtime?

SELECT on the source tables and Vector Search index it queries • EXECUTE on the Unity Catalog functions registered as its tools • USE CATALOG and USE SCHEMA on the containing catalog and schema • plus query permission on any serving endpoint it calls.

PII protection in GenAI apps?

Pre-prompt redaction, post-output filtering, audit logs, customer-managed encryption keys, network isolation.

What are guardrails in a GenAI application and where can they be applied?

Controls that constrain inputs and outputs — topic restriction, unsafe-content filtering, PII detection and refusal behavior. They can be applied in the application chain itself and centrally at the endpoint through AI Gateway safety configuration.

Why is output filtering alone an insufficient defense for a tool-calling agent?

Because the damage from an injected instruction happens when the tool executes — data deleted, an email sent, a record exfiltrated through a tool argument — before any text reaches the output filter. Tool permissions and approval gates must limit the action itself.