100% Latest & Updated Microsoft DP-800 Practice Test Questions, Exam Dumps & Verified Answers!
30 Days Free Updates, Instant Download!
Question 980
A travel-style booking assistant needs live stock levels from SQL. A test instead finds: Assistant offers unavailable quantity despite empty stock. Which underlying issue best explains this finding?
- Retrieval included stale records or skipped freshness filter
- Endpoint authentication or credential configuration is missing
- Endpoint or model deployment name was incorrect
- LLM inferred inventory from stale examples
Explanation
Correct Answer
D:LLM inferred inventory from stale examples. It accounts for the specific observed failure: assistant offers unavailable quantity despite empty stock. The intended solution is retrieve transactional current stock before text generation with the required setup.
Incorrect Answers
A:Retrieval included stale records or skipped freshness filter. This concerns assistant answers with last year's retirement policy. The relevant SQL or system operation is LLM inferred inventory from stale examples.
B:Endpoint authentication or credential configuration is missing. This concerns external rest call fails with unauthorized response. The relevant SQL or system operation is LLM inferred inventory from stale examples.
C:Endpoint or model deployment name was incorrect. This concerns rest request hits wrong model deployment. The relevant SQL or system operation is LLM inferred inventory from stale examples.
Question 981
A support bot routes answers to an external model via REST. Which database design or engineering approach most directly meets this requirement?
- Send only minimum necessary approved fields
- Use RAG to ground generation in current approved records
- Use sp_invoke_external_rest_endpoint where supported and configured
- Prioritize authoritative current source and reconcile conflicts
Explanation
Correct Answer
A:Send only minimum necessary approved fields. The implementation is create sql projection excluding secrets before external request; success can be checked by inspect outbound json for pii and hidden columns. The method addresses the stated data and workload constraint.
Incorrect Answers
B:Use RAG to ground generation in current approved records. This concerns an ai assistant answers questions from frequently changing internal procedures. Instead, send only minimum necessary approved fields.
C:Use sp_invoke_external_rest_endpoint where supported and configured. This concerns a stored procedure sends an allowed request to an external text model. Instead, send only minimum necessary approved fields.
D:Prioritize authoritative current source and reconcile conflicts. This concerns a rag answer includes contradictory facts from old and new records. Instead, send only minimum necessary approved fields.
Question 982
A support bot routes answers to an external model via REST. The team selects: Send only minimum necessary approved fields. Which implementation action puts this design into practice?
- Create scoped credential/endpoint and call stored procedure with JSON payload
- Create SQL projection excluding secrets before external request
- Use FOR JSON PATH or JSON_OBJECT projection of allowed fields
- Configure endpoint address, credentials and model deployment
Explanation
Correct Answer
B:Create SQL projection excluding secrets before external request. This is the concrete setup for send only minimum necessary approved fields, and inspect outbound json for pii and hidden columns supplies a direct confirmation.
Incorrect Answers
A:Create scoped credential/endpoint and call stored procedure with JSON payload. This concerns a stored procedure sends an allowed request to an external text model. Instead, create SQL projection excluding secrets before external request.
C:Use FOR JSON PATH or JSON_OBJECT projection of allowed fields. This is relevant when a chatbot uses SQL result rows as context for a model. Instead, create SQL projection excluding secrets before external request.
D:Configure endpoint address, credentials and model deployment. This concerns connecting SQL retrieval to microsoft foundry model. Instead, create SQL projection excluding secrets before external request.
Question 983
A support bot routes answers to an external model via REST. After implementing the design, which check most directly validates the expected behavior?
- Open cited source and confirm effective date
- Reject malformed response and accept valid typed output
- Inspect outbound JSON for PII and hidden columns
- Test authorized response and telemetry
Explanation
Correct Answer
C:Inspect outbound JSON for PII and hidden columns. This verifies the requirement in the case rather than merely confirming that a job ran; an opposing result can reveal that rag context construction over-shared database columns.
Incorrect Answers
A:Open cited source and confirm effective date. This concerns cite exact source version and timestamp. Instead, inspect outbound JSON for PII and hidden columns.
B:Reject malformed response and accept valid typed output. This is relevant when an assistant produces a json answer that must be stored in SQL. Instead, inspect outbound JSON for PII and hidden columns.
D:Test authorized response and telemetry. This concerns a stored procedure sends an allowed request to an external text model. Instead, inspect outbound JSON for PII and hidden columns.
Question 984
A support bot routes answers to an external model via REST. A test instead finds: External model receives unrelated customer details. Which underlying issue best explains this finding?
- Endpoint authentication or credential configuration is missing
- Retrieval filter ignored effective-date metadata
- RAG context construction over-shared database columns
- SQL rows were flattened without structured context
Explanation
Correct Answer
C:RAG context construction over-shared database columns. It accounts for the specific observed failure: external model receives unrelated customer details. The intended solution is send only minimum necessary approved fields with the required setup.
Incorrect Answers
A:Endpoint authentication or credential configuration is missing. This concerns external rest call fails with unauthorized response. The relevant SQL or system operation is RAG context construction over-shared database columns.
B:Retrieval filter ignored effective-date metadata. This concerns citation points to superseded policy revision. The relevant SQL or system operation is RAG context construction over-shared database columns.
D:SQL rows were flattened without structured context. This concerns llm receives ambiguous comma-separated values. The relevant SQL or system operation is RAG context construction over-shared database columns.
Question 985
A service needs to connect SQL retrieval to Microsoft Foundry model. Which TWO listed actions form the most appropriate database design and its concrete implementation? (Choose TWO.)
- Use sp_invoke_external_rest_endpoint where supported and configured
- Use approved Foundry endpoint and managed authentication
- Configure endpoint address, credentials and model deployment
- Retrieve transactional current stock before text generation
- Use evidence-aware abstention in RAG prompting
Explanation
Correct Answers
B:Use approved Foundry endpoint and managed authentication. The implementation is configure endpoint address, credentials and model deployment; success can be checked by run test prompt and verify output plus usage metrics. The method addresses the stated data and workload constraint.
C:This is the concrete configuration of the specified design: configure endpoint address, credentials and model deployment. The choice makes the implementation testable in the given workload.
Incorrect Answers
A:Use sp_invoke_external_rest_endpoint where supported and configured. This concerns a stored procedure sends an allowed request to an external text model. Instead, use approved Foundry endpoint and managed authentication.
D:Retrieve transactional current stock before text generation. This concerns live stock levels from SQL. Instead, use approved Foundry endpoint and managed authentication.
E:Use evidence-aware abstention in RAG prompting. This concerns not invent answer when SQL retrieval returns no supporting rows. Instead, use approved Foundry endpoint and managed authentication.
Question 986
A service needs to connect SQL retrieval to Microsoft Foundry model. The team selects: Use approved Foundry endpoint and managed authentication. Which implementation action puts this design into practice?
- Configure endpoint address, credentials and model deployment
- Explicitly instruct refusal or escalation when context lacks answer
- Set candidate ranking and token budget for retrieved chunks
- Create scoped credential/endpoint and call stored procedure with JSON payload
Explanation
Correct Answer
A:Configure endpoint address, credentials and model deployment. This is the concrete setup for use approved foundry endpoint and managed authentication, and run test prompt and verify output plus usage metrics supplies a direct confirmation.
Incorrect Answers
B:Explicitly instruct refusal or escalation when context lacks answer. This concerns not invent answer when SQL retrieval returns no supporting rows. Instead, configure endpoint address, credentials and model deployment.
C:Set candidate ranking and token budget for retrieved chunks. This concerns a SQL-backed assistant runs retrieval but sends too many irrelevant rows. Instead, configure endpoint address, credentials and model deployment.
D:Create scoped credential/endpoint and call stored procedure with JSON payload. This concerns a stored procedure sends an allowed request to an external text model. Instead, configure endpoint address, credentials and model deployment.
Question 987
A service needs to connect SQL retrieval to Microsoft Foundry model. After implementing the design, which check most directly validates the expected behavior?
- Test prompt injection phrase embedded in source document
- Run test prompt and verify output plus usage metrics
- Test contradictory version pair yields current rule
- Test out-of-scope question returns grounded uncertainty
Explanation
Correct Answer
B:Run test prompt and verify output plus usage metrics. This verifies the requirement in the case rather than merely confirming that a job ran; an opposing result can reveal that endpoint or model deployment name was incorrect.
Incorrect Answers
A:Test prompt injection phrase embedded in source document. This concerns a reusable prompt with SQL database retrieval. Instead, run test prompt and verify output plus usage metrics.
C:Test contradictory version pair yields current rule. This concerns a rag answer includes contradictory facts from old and new records. Instead, run test prompt and verify output plus usage metrics.
D:Test out-of-scope question returns grounded uncertainty. This concerns not invent answer when SQL retrieval returns no supporting rows. Instead, run test prompt and verify output plus usage metrics.
Question 988
A service needs to connect SQL retrieval to Microsoft Foundry model. A test instead finds: REST request hits wrong model deployment. Which underlying issue best explains this finding?
- Prompt lacks no-evidence behavior or model ignored it
- Endpoint or model deployment name was incorrect
- Endpoint authentication or credential configuration is missing
- No evaluated ground-truth and citation evidence exists
Explanation
Correct Answer
B:Endpoint or model deployment name was incorrect. It accounts for the specific observed failure: rest request hits wrong model deployment. The intended solution is use approved foundry endpoint and managed authentication with the required setup.
Incorrect Answers
A:Prompt lacks no-evidence behavior or model ignored it. This concerns assistant confidently makes up non-existent product policy. Here, endpoint or model deployment name was incorrect.
C:Endpoint authentication or credential configuration is missing. This concerns external rest call fails with unauthorized response. Here, endpoint or model deployment name was incorrect.
D:No evaluated ground-truth and citation evidence exists. This concerns team declares success from fluent demos only. Here, endpoint or model deployment name was incorrect.
Question 989
An application wants to check whether RAG helped over unguided prompts. Which database design or engineering approach most directly meets this requirement?
- Run retrieval under requesting user's authorized context
- Retrieve transactional current stock before text generation
- Use groundedness, relevance and citation-based evaluation
- Redact sensitive prompts and protect model invocation logging
Explanation
Correct Answer
C:Use groundedness, relevance and citation-based evaluation. The implementation is create holdout questions with known supporting passages; success can be checked by compare hallucination rate and answer citation accuracy. The method addresses the stated data and workload constraint.
Incorrect Answers
A:Run retrieval under requesting user's authorized context. This concerns rag that respects row-level security. Instead, use groundedness, relevance and citation-based evaluation.
B:Retrieve transactional current stock before text generation. This concerns live stock levels from SQL. Instead, use groundedness, relevance and citation-based evaluation.
D:Redact sensitive prompts and protect model invocation logging. This is relevant when a compliance rag app cannot expose secrets in query logs. Instead, use groundedness, relevance and citation-based evaluation.
Question 990
An application wants to check whether RAG helped over unguided prompts. The team selects: Use groundedness, relevance and citation-based evaluation. Which implementation action puts this design into practice?
- Use FOR JSON PATH or JSON_OBJECT projection of allowed fields
- Create holdout questions with known supporting passages
- Retrieve authorized current passages and pass them with question
- Apply RLS predicate and per-document ACL before prompt construction
Explanation
Correct Answer
B:Create holdout questions with known supporting passages. This is the concrete setup for use groundedness, relevance and citation-based evaluation, and compare hallucination rate and answer citation accuracy supplies a direct confirmation.
Incorrect Answers
A:Use FOR JSON PATH or JSON_OBJECT projection of allowed fields. This is relevant when a chatbot uses SQL result rows as context for a model. Instead, create holdout questions with known supporting passages.
C:Retrieve authorized current passages and pass them with question. This concerns an ai assistant answers questions from frequently changing internal procedures. Instead, create holdout questions with known supporting passages.
D:Apply RLS predicate and per-document ACL before prompt construction. This concerns rag that respects row-level security. Instead, create holdout questions with known supporting passages.
Developing AI-Enabled Database Solutions (DP-800) Practice Tests