Black Friday Reward - Upto 75% off - Ends in 0d 00h 00m 00s - Coupon code: CFsave75

Pass the Databricks Context Engineer Context-Engineer-Associate Questions and answers with CertsForce

Viewing page 2 out of 2 pages
Viewing questions 11-20 out of questions
Questions # 11:

A context engineer is building a compound AI system for a hospital network with Agent Bricks Custom Agents. The system answers clinician questions about a specific patient’s medication history. Patient records are stored in a Delta table that is continuously updated as new prescriptions, refills, and discontinuations are recorded, and clinicians must see the most current state of a patient’s record when they submit a query. HIPAA’s minimum necessary rule requires the system to retrieve only the requesting patient’s records instead of searching across the broader patient population. End-to-end latency per query must stay under two seconds.

Which retrieval strategy should the context engineer use?

Options:

A.

Use a Databricks AI Search index configured in delta-sync mode so the index automatically updates from the Delta table, and perform semantic retrieval at inference.


B.

Use just-in-time agentic retrieval by equipping the agent with a tool that executes a parameterized Delta table query scoped to the specific patient at inference time.


C.

Use a hybrid approach: precompute embeddings for all patient records nightly and supplement with just-in-time retrieval only for records modified during the day.


D.

Use pre-inference embedding-based retrieval by indexing all patient records into a Databricks AI Search index at pipeline build time and querying it semantically at inference.


Questions # 12:

A context engineer is examining an MLflow trace for a Databricks compliance agent mid-workflow on a quarterly regulatory review for a regional bank. The agent’s design pattern is to retrieve regulatory clauses, extract structured obligations with regional metadata and source citations, validate each obligation through the rules engine, and synthesize the audit memo from the structured intermediate plus the validation outcomes. The context window is nearing the compaction threshold, and compaction will fire before the workflow is complete.

The trace includes three executed spans and one queued span:

Span 1 (RETRIEVER): Retrieved 22 regulatory clause excerpts from the compliance vector index. Output: 22 documents (8,400 tokens) of raw clause text with metadata for source URI and section ID.

Span 2 (LLM/CHAT_MODEL): Produced a structured intermediate (410 tokens) containing three extracted compliance obligations, each annotated with a regional applicability tag describing how the bank’s state-level regulations modify the federal requirement and a source citation pointing back to the originating clause.

Span 3 (TOOL): Ran the three obligations through the rules engine and returned a structured pass/fail report (280 tokens) with one outcome entry per obligation. Each entry contains the obligation ID, the pass/fail value, and a brief explanation of the rule that determined the outcome.

Span 4 (LLM/CHAT_MODEL, queued): Will draft the compliance memo for the bank’s audit team.

Which content from the executed spans can the compactor safely summarize without affecting span 4’s execution?

Options:

A.

The 22 raw clause excerpts from span 1, because their content has been transferred forward by span 2 into the structured intermediate (with regional applicability tags and source citations preserved) that the memo synthesis works from.


B.

The structured intermediate output from span 2, because span 1’s raw regulatory clauses are the canonical source preserved verbatim for the memo’s direct source quotations and audit traceability, while span 2’s extracted obligations are intermediate analysis, the rules engine has already factored into the pass/fail report.


C.

All three executed spans, because the default compaction summary captures the agent’s state and findings, and span 4 will draft the memo from the digest, which preserves the agent’s analysis at the level needed for synthesis.


D.

The 22 raw clause excerpts from span 1 and the structured intermediate output from span 2, because everything that has been processed by a downstream operation is redundant in the active context; the pass/fail report from span 3 is the only output still doing work for the queued span.


Questions # 13:

A context engineer is investigating a multi-agent pipeline on Databricks where a coordinating agent breaks down a document analysis task and dispatches subtasks to three specialized sub-agents. After deployment, the sub-agents produce outputs that are internally consistent but contradict one another and do not reflect earlier inferences made at the pipeline level. The sub-agents have access to the same retrieval index, the embedding model is verified as current, and individual sub-agent outputs are accurate when tested in isolation with full context supplied manually.

What is a reasonable root cause of the downstream failures?

Options:

A.

The coordinating agent’s temperature parameter is set too high, introducing non-determinism into the subtask decomposition and producing inconsistent dispatch instructions.


B.

Each sub-agent is dispatched with only its individual task message and lacks access to the coordinator’s earlier reasoning, tool outputs, and decisions.


C.

The retrieval index used by the sub-agents is misconfigured, so they are querying a different corpus than the coordinating agent, leading to contradictory but locally consistent outputs.


D.

The embedding model used for retrieval was not trained on the document domain, causing sub-agents to retrieve irrelevant chunks and produce contradictory summaries.


Questions # 14:

A context engineer is building a regulatory compliance agent on Databricks that connects to an external compliance management platform through an MCP Service registered in Unity Catalog.

The MCP server exposes the following tools:

search_compliance_records: Retrieves existing compliance records without modifying them.

get_submission_status: Checks the status of previously submitted reports.

submit_regulatory_report: Sends a finalized regulatory report to an external authority.

delete_compliance_record: Permanently deletes an existing compliance record.

The agent serves compliance officers who are authorized to retrieve records and submit reports. However, organizational policy requires explicit human approval before every regulatory report submission.

The agent must continue executing read-only tools without interruption. It must also prevent unauthorized destructive operations and maintain an auditable record of tool invocations.

The engineering team has confirmed that the MCP tools function correctly. The remaining requirement is to enforce the approval and authorization rules at the platform governance layer rather than relying exclusively on instructions inside the agent ' s system prompt.

Which approach should the context engineer implement?

Options:

A.

Add instructions to the system prompt requiring the agent to ask the user for confirmation before invoking submit_regulatory_report, and instruct the agent never to invoke delete_compliance_record.


B.

Increase the model ' s reasoning effort so the agent evaluates the consequences of each MCP invocation before deciding whether user approval is necessary.


C.

Configure the MCP Service with appropriate Unity Catalog permissions and tool restrictions, and attach an input-phase service policy that requires approval for submit_regulatory_report while allowing authorized read-only calls.


D.

Remove all tools capable of modifying external systems from the MCP server and require compliance officers to submit regulatory reports through an independent manual process.


Questions # 15:

A context engineer is evaluating a Databricks agent deployed for a manufacturing company’s field service team. The agent uses a DELTA_SYNC Databricks AI Search index to search a knowledge base of equipment troubleshooting guides. The product line includes closely related models (CX-400, CX-410, CX-420) whose guides use similar procedural language but specify different part numbers, torque values, and calibration sequences for each model. The index uses databricks-gte-large-en embeddings with a chunk_size of 512 tokens and a chunk_overlap of 50 tokens. Evaluation shows that when a technician queries for a specific model, such as “CX-400 belt tensioner replacement procedure,” the agent frequently returns procedures for a different model in the same product family. The returned content appears relevant but contains incorrect part numbers and specifications for the queried model.

Which Databricks AI Search configuration change directly addresses this retrieval pattern?

Options:

A.

Set query_type to HYBRID so that the search combines semantic matching with keyword matching, merging both result sets with Reciprocal Rank Fusion.


B.

Switch the embedding model to databricks-bge-large-en and configure the recommended query instruction to improve alignment between technician queries and guide passages.


C.

Reduce chunk_size from 512 to 128 tokens so that each chunk contains a narrower passage where model-specific details like part numbers dominate the embedding.


D.

Add columns_to_rerank with the built-in reranker to reorder initial search results so that the most model-specific passages rank highest.


Viewing page 2 out of 2 pages
Viewing questions 11-20 out of questions