質問 1：
A context engineer is developing a Databricks agent for a financial research platform that answers analyst queries using a vector search index over earnings reports. The agent uses a 180-token system prompt, a 250- token conversation history window, and a RAG pipeline that retrieves 8 document chunks at runtime. Each chunk contains 550 tokens, contributing 4,400 tokens of retrieved context. The model's context window is
8,192 tokens, leaving just 3,362 tokens for the analyst query and model response. Profiling shows that the retrieved chunks consistently contain repetitive regulatory boilerplate and duplicated table headers that are rarely cited in the model's final answers.
Which two changes should the context engineer make to reduce the token footprint of retrieved context without discarding relevant financial content?
Choose two
A. Expand the conversation history window from 250 tokens to 900 tokens to improve multi-turn coherence across analyst sessions and offset token pressure from the retrieved chunks.
B. Re-index the earnings reports using a finer-grained embedding model to improve retrieval precision, surfacing more relevant passages without altering chunk boundaries or stripping metadata.
C. Switch the retrieval strategy from cosine similarity to MMR to increase diversity across retrieved chunks, reducing redundancy between chunks without modifying chunk size or removing boilerplate.
D. Reduce each chunk from 550 tokens to 150-200 tokens by splitting at semantic boundaries and stripping repeated regulatory boilerplate and duplicate headers before indexing.
E. Reduce retrieved chunks from 8 to 3 and apply a reranker to select the highest-relevance chunks, preserving pertinent financial content while cutting injected tokens by over 60%.
正解：D,E
解説: (Pass4Test メンバーにのみ表示されます)
質問 2：
A context engineer is preparing to deploy a per-tenant Databricks agent for a SaaS retail analytics platform.
Each platform customer is provisioned with their own Unity Catalog catalog, retail_ & lt;customer & gt;, and within each tenant catalog, data is organized by business domain rather than by origin.
The sales schema contains the customer's POS transaction and returns tables, which the customer's source systems write to throughout the day, alongside the daily_sales_by_store, hourly_revenue_by_category, and top_skus_weekly summary tables that a nightly Lakeflow Jobs pipeline produces by reading those POS tables. The inventory schema contains stock-level and inbound-shipment tables written continuously by ingestion, alongside demand_forecast_7d and reorder_suggestions tables produced by the SaaS's ML pipelines. The customer schema contains customer master records and contact tables, all populated by ingestion.
The SaaS deploys one agent per customer through Model Serving, and each agent has its own service principal. Before any agent endpoint is registered, the governance requirements are that an agent for a given customer must be able to retrieve data only from that customer's catalog and never from another customer's catalog, and that within its own customer's catalog, the agent must be able to retrieve only from tables populated directly by the customer's ingestion pipelines, never from nightly summaries, forecasts, or other tables produced by SaaS pipelines.
Which governance approach should the context engineer implement for each tenant's agent before registration?
A. For each tenant's agent service principal, grant USE CATALOG only on that tenant's retail_ < customer > catalog and USE SCHEMA together with SELECT on the sales, inventory, and customer schemas, relying on the per-tenant catalog boundary to scope retrieval to the customer's data.
B. For each tenant's agent service principal, grant USE CATALOG only on that tenant's retail_ < customer > catalog and, within that catalog, grant USE SCHEMA on each domain schema together with table-level SELECT only on the tables populated by the customer's ingestion pipelines. Leave the nightly summary, forecast, and other SaaS-produced tables in those schemas ungranted.
C. Provision a single agent service principal shared across all tenants because per-tenant service principals are operationally heavy at the SaaS's expected scale. Grant the shared service principal USE CATALOG on every retail_ < customer > catalog and table-level SELECT only on the ingestion-fed tables in each catalog. Configure the agent's retrieval tool to inject the requesting customer's catalog name into every query so the agent reads only the right tenant's tables at request time.
D. For each tenant's agent service principal, grant USE CATALOG on that tenant's retail_ < customer > catalog and USE SCHEMA together with SELECT on the sales, inventory, and customer schemas.
Apply a Unity Catalog tag source=ingest to every ingestion-fed table across the tenant catalogs and configure each agent's retrieval logic to issue queries only against tables carrying that tag.
正解：B
解説: (Pass4Test メンバーにのみ表示されます)
質問 3：
A context engineer is assessing a Databricks agent that coordinates a multi-week pharmaceutical supply chain compliance workflow across dozens of distribution centers. The agent uses a flat task decomposition strategy, dividing the entire workflow into a single-level list of atomic tasks that are dispatched and tracked independently. The workflow contains clusters of tightly coupled sub-tasks, such as per-facility inspection records that must all complete before a regional compliance certificate can be issued, and the agent repeatedly fails to coordinate these cluster-level completions correctly. Logs show that the agent loses track of intermediate group states, issues compliance certificates prematurely on incomplete facility data, and cannot recover gracefully when individual facility inspection tasks fail.
Which two changes should the context engineer make to resolve the observed failure?
Choose two
A. Introduce explicit dependency gates at each cluster boundary so the compliance certificate task is dispatched only after all facility inspection tasks in the group have reached a confirmed completed state.
B. Replace the workflow with a fixed sequential chaining strategy that executes every facility inspection one at a time before issuing any certificate, eliminating all concurrency from the pipeline.
C. Add a retry loop at the top-level agent that restarts the entire flat task list from the beginning whenever any single facility inspection task fails, ensuring no partial state persists across runs.
D. Switch to a parallel decomposition strategy that executes all facility inspection and certificate tasks simultaneously, relying on eventual consistency to merge partial results into the final compliance record.
E. Replace the flat task decomposition with a hierarchical decomposition strategy that groups related facility inspection sub-tasks under a parent node, enabling group-level completion tracking before dependent tasks proceed.
正解：A,E
解説: (Pass4Test メンバーにのみ表示されます)
質問 4：
A context engineer is configuring a Databricks agent for an automotive service center platform. The agent must serve service center staff who submit a vehicle identification number (VIN) and a reported symptom.
The agent is expected to return a summary of the vehicle's operating profile, identify the applicable SOP procedure code for the symptom, and retrieve the narrative step-by-step service instructions for that procedure. The engineer has access to these data sources:
Unity Catalog Delta table named vehicle_profiles with columns vin, engine_type, and operating_spec.
Unity Catalog Delta table named symptom_sop_map with columns symptom_code and sop_procedure_code.
Unity Catalog Delta table named service_history with columns vin, service_date, and technician_id.
Databricks AI Search index built from scanned OEM service manuals containing narrative SOP instructions and safety warnings.
Which combination of context elements correctly supports the agent's task?
A. A system prompt scoping the agent as an automotive service assistant; a generic instruction to query available structured Delta tables for any structured lookup based on provided identifiers; and the Databricks AI Search index for retrieving narrative OEM service instructions.
B. A system prompt scoping the agent as an automotive service assistant; tool-use instructions mapping vehicle_profiles to VIN-based operating profile lookups and symptom_sop_map to symptom-to- procedure-code resolution; and the Databricks AI Search index for retrieving narrative OEM service instructions.
C. A system prompt scoping the agent as an automotive service assistant; explicit tool-use instructions mapping service_history to VIN-based operating profile lookups and symptom_sop_map to symptom- to-procedure-code resolution; and the Databricks AI Search index for retrieving narrative OEM service instructions.
D. A system prompt scoping the agent as an automotive service assistant; explicit tool-use instructions mapping vehicle_profiles to VIN-based operating profile lookups; and the Databricks AI Search index for both procedure code resolution and narrative OEM service instructions, relying on semantic search to surface structured codes from manual text.
正解：B
解説: (Pass4Test メンバーにのみ表示されます)
質問 5：
A context engineer maintains a Databricks-based assistant for a fraud investigation team. Each investigation is a long-running thread that the team works on across many sessions over weeks or months. Investigations are typically handled by two or three analysts who rotate in and out as new evidence arrives, and any one analyst is usually working several open investigations at the same time. The assistant runs on Agent Bricks Custom Agents with a single retrieval tool over a Databricks AI Search index of the team's case file corpus (incident reports, suspect dossiers, transaction logs, exhibits), synced nightly from the source Delta tables that the case management system writes to. The retrieval tool is called with num_results=50. The system has been in production for nine months.
The team begins reporting that the assistant treats every new session as a cold start. The most recent example:
on Friday, analyst A and the assistant work together on an active investigation. By the end of the session, they have eliminated two suspects on alibi evidence, confirmed a third as the likely actor, and identified two specific accounts as the transfer pathway for the funds in question. On Monday, analyst B opens the assistant against the same investigation to draft the next subpoena request. The assistant responds by asking who the suspect is, what the eliminations were, and which accounts are in scope. The engineer reproduces the pattern across other investigations: within a single session, the assistant reasons well; the next session, regardless of which analyst opens it, starts cold.
What change should the engineer make to address this pattern?
A. Add a case-scoped persistent memory store (a Unity Catalog Delta table keyed by case_id) and wire the agent with a tool that writes a structured summary of each session's conclusions (eliminations, confirmations, key entities, decisions) to the store at session end and a tool that fetches the active case's entries at session start so the prior conclusions enter the context before the analyst's first message.
B. Replace the nightly Delta sync on the case index with Lakeflow Connect streaming ingestion so that the most recent activity on the investigation lands in the vector index within minutes of being created and is available at every session start.
C. Add a per-analyst session history store (a Unity Catalog Delta table keyed by analyst user ID where the agent appends each completed session's conversation transcript) and have the assistant fetch the analyst' s recent transcripts at session start and include them in the context so prior work carries over.
D. Raise num_results on the case vector index from 50 to 150 and add a client-side similarity-score floor of 0.25, so that a wider net of case-relevant chunks reaches the assistant at the start of each session and the prior context surfaces alongside the analyst's first message.
正解：A
解説: (Pass4Test メンバーにのみ表示されます)
質問 6：
A context engineer is troubleshooting a Databricks agent responsible for a multi-month clinical trial data processing pipeline. The agent uses a fixed sequential chaining strategy, running each processing stage in a predetermined order regardless of which stages have already completed successfully. When upstream data sources are delayed or partially available, the agent restarts the entire chain from the beginning, discarding all previously completed stage outputs. Logs show that stages with no dependency on the delayed source are being blocked unnecessarily, and total pipeline runtime has grown to an unacceptable length because of repeated full restarts on partial failures.
Which two changes should the context engineer make to resolve the observed failure pattern?
Choose two
A. Increase the agent's retry limit and timeout thresholds so the sequential chain has more time to wait for delayed upstream data before failing.
B. Replace the fixed sequential chain with a dependency-graph-aware strategy that allows independent stages to execute without waiting for unrelated delayed stages.
C. Introduce checkpointing so that successfully completed stages are persisted and the agent resumes from the last valid checkpoint rather than restarting the full chain.
D. Replace the agent's task planner with a reactive event-driven model that triggers each stage only when a new data file lands in the source directory.
E. Switch to a parallel decomposition strategy so all stages execute simultaneously, eliminating the sequential bottleneck caused by delayed upstream sources.
正解：B,C
解説: (Pass4Test メンバーにのみ表示されます)
A context engineer is developing a Databricks agent for a financial research platform that answers analyst queries using a vector search index over earnings reports. The agent uses a 180-token system prompt, a 250- token conversation history window, and a RAG pipeline that retrieves 8 document chunks at runtime. Each chunk contains 550 tokens, contributing 4,400 tokens of retrieved context. The model's context window is
8,192 tokens, leaving just 3,362 tokens for the analyst query and model response. Profiling shows that the retrieved chunks consistently contain repetitive regulatory boilerplate and duplicated table headers that are rarely cited in the model's final answers.
Which two changes should the context engineer make to reduce the token footprint of retrieved context without discarding relevant financial content?
Choose two
A. Expand the conversation history window from 250 tokens to 900 tokens to improve multi-turn coherence across analyst sessions and offset token pressure from the retrieved chunks.
B. Re-index the earnings reports using a finer-grained embedding model to improve retrieval precision, surfacing more relevant passages without altering chunk boundaries or stripping metadata.
C. Switch the retrieval strategy from cosine similarity to MMR to increase diversity across retrieved chunks, reducing redundancy between chunks without modifying chunk size or removing boilerplate.
D. Reduce each chunk from 550 tokens to 150-200 tokens by splitting at semantic boundaries and stripping repeated regulatory boilerplate and duplicate headers before indexing.
E. Reduce retrieved chunks from 8 to 3 and apply a reranker to select the highest-relevance chunks, preserving pertinent financial content while cutting injected tokens by over 60%.
正解：D,E
解説: (Pass4Test メンバーにのみ表示されます)
質問 2：
A context engineer is preparing to deploy a per-tenant Databricks agent for a SaaS retail analytics platform.
Each platform customer is provisioned with their own Unity Catalog catalog, retail_ & lt;customer & gt;, and within each tenant catalog, data is organized by business domain rather than by origin.
The sales schema contains the customer's POS transaction and returns tables, which the customer's source systems write to throughout the day, alongside the daily_sales_by_store, hourly_revenue_by_category, and top_skus_weekly summary tables that a nightly Lakeflow Jobs pipeline produces by reading those POS tables. The inventory schema contains stock-level and inbound-shipment tables written continuously by ingestion, alongside demand_forecast_7d and reorder_suggestions tables produced by the SaaS's ML pipelines. The customer schema contains customer master records and contact tables, all populated by ingestion.
The SaaS deploys one agent per customer through Model Serving, and each agent has its own service principal. Before any agent endpoint is registered, the governance requirements are that an agent for a given customer must be able to retrieve data only from that customer's catalog and never from another customer's catalog, and that within its own customer's catalog, the agent must be able to retrieve only from tables populated directly by the customer's ingestion pipelines, never from nightly summaries, forecasts, or other tables produced by SaaS pipelines.
Which governance approach should the context engineer implement for each tenant's agent before registration?
A. For each tenant's agent service principal, grant USE CATALOG only on that tenant's retail_ < customer > catalog and USE SCHEMA together with SELECT on the sales, inventory, and customer schemas, relying on the per-tenant catalog boundary to scope retrieval to the customer's data.
B. For each tenant's agent service principal, grant USE CATALOG only on that tenant's retail_ < customer > catalog and, within that catalog, grant USE SCHEMA on each domain schema together with table-level SELECT only on the tables populated by the customer's ingestion pipelines. Leave the nightly summary, forecast, and other SaaS-produced tables in those schemas ungranted.
C. Provision a single agent service principal shared across all tenants because per-tenant service principals are operationally heavy at the SaaS's expected scale. Grant the shared service principal USE CATALOG on every retail_ < customer > catalog and table-level SELECT only on the ingestion-fed tables in each catalog. Configure the agent's retrieval tool to inject the requesting customer's catalog name into every query so the agent reads only the right tenant's tables at request time.
D. For each tenant's agent service principal, grant USE CATALOG on that tenant's retail_ < customer > catalog and USE SCHEMA together with SELECT on the sales, inventory, and customer schemas.
Apply a Unity Catalog tag source=ingest to every ingestion-fed table across the tenant catalogs and configure each agent's retrieval logic to issue queries only against tables carrying that tag.
正解：B
解説: (Pass4Test メンバーにのみ表示されます)
質問 3：
A context engineer is assessing a Databricks agent that coordinates a multi-week pharmaceutical supply chain compliance workflow across dozens of distribution centers. The agent uses a flat task decomposition strategy, dividing the entire workflow into a single-level list of atomic tasks that are dispatched and tracked independently. The workflow contains clusters of tightly coupled sub-tasks, such as per-facility inspection records that must all complete before a regional compliance certificate can be issued, and the agent repeatedly fails to coordinate these cluster-level completions correctly. Logs show that the agent loses track of intermediate group states, issues compliance certificates prematurely on incomplete facility data, and cannot recover gracefully when individual facility inspection tasks fail.
Which two changes should the context engineer make to resolve the observed failure?
Choose two
A. Introduce explicit dependency gates at each cluster boundary so the compliance certificate task is dispatched only after all facility inspection tasks in the group have reached a confirmed completed state.
B. Replace the workflow with a fixed sequential chaining strategy that executes every facility inspection one at a time before issuing any certificate, eliminating all concurrency from the pipeline.
C. Add a retry loop at the top-level agent that restarts the entire flat task list from the beginning whenever any single facility inspection task fails, ensuring no partial state persists across runs.
D. Switch to a parallel decomposition strategy that executes all facility inspection and certificate tasks simultaneously, relying on eventual consistency to merge partial results into the final compliance record.
E. Replace the flat task decomposition with a hierarchical decomposition strategy that groups related facility inspection sub-tasks under a parent node, enabling group-level completion tracking before dependent tasks proceed.
正解：A,E
解説: (Pass4Test メンバーにのみ表示されます)
質問 4：
A context engineer is configuring a Databricks agent for an automotive service center platform. The agent must serve service center staff who submit a vehicle identification number (VIN) and a reported symptom.
The agent is expected to return a summary of the vehicle's operating profile, identify the applicable SOP procedure code for the symptom, and retrieve the narrative step-by-step service instructions for that procedure. The engineer has access to these data sources:
Unity Catalog Delta table named vehicle_profiles with columns vin, engine_type, and operating_spec.
Unity Catalog Delta table named symptom_sop_map with columns symptom_code and sop_procedure_code.
Unity Catalog Delta table named service_history with columns vin, service_date, and technician_id.
Databricks AI Search index built from scanned OEM service manuals containing narrative SOP instructions and safety warnings.
Which combination of context elements correctly supports the agent's task?
A. A system prompt scoping the agent as an automotive service assistant; a generic instruction to query available structured Delta tables for any structured lookup based on provided identifiers; and the Databricks AI Search index for retrieving narrative OEM service instructions.
B. A system prompt scoping the agent as an automotive service assistant; tool-use instructions mapping vehicle_profiles to VIN-based operating profile lookups and symptom_sop_map to symptom-to- procedure-code resolution; and the Databricks AI Search index for retrieving narrative OEM service instructions.
C. A system prompt scoping the agent as an automotive service assistant; explicit tool-use instructions mapping service_history to VIN-based operating profile lookups and symptom_sop_map to symptom- to-procedure-code resolution; and the Databricks AI Search index for retrieving narrative OEM service instructions.
D. A system prompt scoping the agent as an automotive service assistant; explicit tool-use instructions mapping vehicle_profiles to VIN-based operating profile lookups; and the Databricks AI Search index for both procedure code resolution and narrative OEM service instructions, relying on semantic search to surface structured codes from manual text.
正解：B
解説: (Pass4Test メンバーにのみ表示されます)
質問 5：
A context engineer maintains a Databricks-based assistant for a fraud investigation team. Each investigation is a long-running thread that the team works on across many sessions over weeks or months. Investigations are typically handled by two or three analysts who rotate in and out as new evidence arrives, and any one analyst is usually working several open investigations at the same time. The assistant runs on Agent Bricks Custom Agents with a single retrieval tool over a Databricks AI Search index of the team's case file corpus (incident reports, suspect dossiers, transaction logs, exhibits), synced nightly from the source Delta tables that the case management system writes to. The retrieval tool is called with num_results=50. The system has been in production for nine months.
The team begins reporting that the assistant treats every new session as a cold start. The most recent example:
on Friday, analyst A and the assistant work together on an active investigation. By the end of the session, they have eliminated two suspects on alibi evidence, confirmed a third as the likely actor, and identified two specific accounts as the transfer pathway for the funds in question. On Monday, analyst B opens the assistant against the same investigation to draft the next subpoena request. The assistant responds by asking who the suspect is, what the eliminations were, and which accounts are in scope. The engineer reproduces the pattern across other investigations: within a single session, the assistant reasons well; the next session, regardless of which analyst opens it, starts cold.
What change should the engineer make to address this pattern?
A. Add a case-scoped persistent memory store (a Unity Catalog Delta table keyed by case_id) and wire the agent with a tool that writes a structured summary of each session's conclusions (eliminations, confirmations, key entities, decisions) to the store at session end and a tool that fetches the active case's entries at session start so the prior conclusions enter the context before the analyst's first message.
B. Replace the nightly Delta sync on the case index with Lakeflow Connect streaming ingestion so that the most recent activity on the investigation lands in the vector index within minutes of being created and is available at every session start.
C. Add a per-analyst session history store (a Unity Catalog Delta table keyed by analyst user ID where the agent appends each completed session's conversation transcript) and have the assistant fetch the analyst' s recent transcripts at session start and include them in the context so prior work carries over.
D. Raise num_results on the case vector index from 50 to 150 and add a client-side similarity-score floor of 0.25, so that a wider net of case-relevant chunks reaches the assistant at the start of each session and the prior context surfaces alongside the analyst's first message.
正解：A
解説: (Pass4Test メンバーにのみ表示されます)
質問 6：
A context engineer is troubleshooting a Databricks agent responsible for a multi-month clinical trial data processing pipeline. The agent uses a fixed sequential chaining strategy, running each processing stage in a predetermined order regardless of which stages have already completed successfully. When upstream data sources are delayed or partially available, the agent restarts the entire chain from the beginning, discarding all previously completed stage outputs. Logs show that stages with no dependency on the delayed source are being blocked unnecessarily, and total pipeline runtime has grown to an unacceptable length because of repeated full restarts on partial failures.
Which two changes should the context engineer make to resolve the observed failure pattern?
Choose two
A. Increase the agent's retry limit and timeout thresholds so the sequential chain has more time to wait for delayed upstream data before failing.
B. Replace the fixed sequential chain with a dependency-graph-aware strategy that allows independent stages to execute without waiting for unrelated delayed stages.
C. Introduce checkpointing so that successfully completed stages are persisted and the agent resumes from the last valid checkpoint rather than restarting the full chain.
D. Replace the agent's task planner with a reactive event-driven model that triggers each stage only when a new data file lands in the source directory.
E. Switch to a parallel decomposition strategy so all stages execute simultaneously, eliminating the sequential bottleneck caused by delayed upstream sources.
正解：B,C
解説: (Pass4Test メンバーにのみ表示されます)
0 お客様のコメント