100% Latest & Updated Microsoft DP-800 Practice Test Questions, Exam Dumps & Verified Answers!
30 Days Free Updates, Instant Download!
Question 950
A chatbot uses SQL result rows as context for a model. The team selects: Serialize controlled result fields to JSON. Which implementation action puts this design into practice?
- Use JSON_VALUE or OPENJSON with schema checks
- Create scoped credential/endpoint and call stored procedure with JSON payload
- Use FOR JSON PATH or JSON_OBJECT projection of allowed fields
- Configure endpoint address, credentials and model deployment
Explanation
Correct Answer
C:Use FOR JSON PATH or JSON_OBJECT projection of allowed fields. This is the concrete setup for serialize controlled result fields to json, and parse payload and verify required field names and types supplies a direct confirmation.
Incorrect Answers
A:Use JSON_VALUE or OPENJSON with schema checks. This is relevant when an assistant produces a json answer that must be stored in SQL. Instead, use FOR JSON PATH or JSON_OBJECT projection of allowed fields.
B: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, use FOR JSON PATH or JSON_OBJECT projection of allowed fields.
D:Configure endpoint address, credentials and model deployment. This concerns connecting SQL retrieval to microsoft foundry model. Instead, use FOR JSON PATH or JSON_OBJECT projection of allowed fields.
Question 951
A chatbot uses SQL result rows as context for a model. After implementing the design, which check most directly validates the expected behavior?
- Evaluate keyword and paraphrase cases in same test suite
- Measure answer quality and input token count
- Parse payload and verify required field names and types
- Run test prompt and verify output plus usage metrics
Explanation
Correct Answer
C:Parse payload and verify required field names and types. This verifies the requirement in the case rather than merely confirming that a job ran; an opposing result can reveal that sql rows were flattened without structured context.
Incorrect Answers
A:Evaluate keyword and paraphrase cases in same test suite. This concerns hybrid SQL/vector candidates before generating answer. Instead, parse payload and verify required field names and types.
B:Measure answer quality and input token count. This concerns a SQL-backed assistant runs retrieval but sends too many irrelevant rows. Instead, parse payload and verify required field names and types.
D:Run test prompt and verify output plus usage metrics. This concerns connecting SQL retrieval to microsoft foundry model. Instead, parse payload and verify required field names and types.
Question 952
A chatbot uses SQL result rows as context for a model. A test instead finds: LLM receives ambiguous comma-separated values. Which underlying issue best explains this finding?
- Context was flooded with low-relevance passages
- Endpoint authentication or credential configuration is missing
- Prompt lacks no-evidence behavior or model ignored it
- SQL rows were flattened without structured context
Explanation
Correct Answer
D:SQL rows were flattened without structured context. It accounts for the specific observed failure: llm receives ambiguous comma-separated values. The intended solution is serialize controlled result fields to json with the required setup.
Incorrect Answers
A:Context was flooded with low-relevance passages. This concerns token cost spikes without improved grounding. The relevant SQL or system operation is SQL rows were flattened without structured context.
B:Endpoint authentication or credential configuration is missing. This concerns external rest call fails with unauthorized response. The relevant SQL or system operation is SQL rows were flattened without structured context.
C:Prompt lacks no-evidence behavior or model ignored it. This concerns assistant confidently makes up non-existent product policy. The relevant SQL or system operation is SQL rows were flattened without structured context.
Question 953
An assistant produces a JSON answer that must be stored in SQL. Which database design or engineering approach most directly meets this requirement?
- Validate and extract model JSON response before persistence
- Serialize controlled result fields to JSON
- Use sp_invoke_external_rest_endpoint where supported and configured
- Use RAG to ground generation in current approved records
Explanation
Correct Answer
A:Validate and extract model JSON response before persistence. The implementation is use json_value or openjson with schema checks; success can be checked by reject malformed response and accept valid typed output. The method addresses the stated data and workload constraint.
Incorrect Answers
B:Serialize controlled result fields to JSON. This is relevant when a chatbot uses SQL result rows as context for a model. Here, validate and extract model JSON response before persistence.
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. Here, validate and extract model JSON response before persistence.
D:Use RAG to ground generation in current approved records. This concerns an ai assistant answers questions from frequently changing internal procedures. Here, validate and extract model JSON response before persistence.
Question 954
An assistant produces a JSON answer that must be stored in SQL. The team selects: Validate and extract model JSON response before persistence. Which implementation action puts this design into practice?
- Use FOR JSON PATH or JSON_OBJECT projection of allowed fields
- Use JSON_VALUE or OPENJSON with schema checks
- Create scoped credential/endpoint and call stored procedure with JSON payload
- Configure audited redaction and role-based log access
Explanation
Correct Answer
B:Use JSON_VALUE or OPENJSON with schema checks. This is the concrete setup for validate and extract model json response before persistence, and reject malformed response and accept valid typed output 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, use JSON_VALUE or OPENJSON with schema checks.
C: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, use JSON_VALUE or OPENJSON with schema checks.
D:Configure audited redaction and role-based log access. This is relevant when a compliance rag app cannot expose secrets in query logs. Instead, use JSON_VALUE or OPENJSON with schema checks.
Question 955
An assistant produces a JSON answer that must be stored in SQL. After implementing the design, which check most directly validates the expected behavior?
- Test authorized response and telemetry
- Reject malformed response and accept valid typed output
- Verify generated answer cites valid current passage
- Compare retrieved source IDs for different users
Explanation
Correct Answer
B:Reject malformed response and accept valid typed output. This verifies the requirement in the case rather than merely confirming that a job ran; an opposing result can reveal that response wasn't parsed and schema validated.
Incorrect Answers
A:Test authorized response and telemetry. This concerns a stored procedure sends an allowed request to an external text model. Instead, reject malformed response and accept valid typed output.
C:Verify generated answer cites valid current passage. This concerns an ai assistant answers questions from frequently changing internal procedures. Instead, reject malformed response and accept valid typed output.
D:Compare retrieved source IDs for different users. This concerns rag that respects row-level security. Instead, reject malformed response and accept valid typed output.
Question 956
An assistant produces a JSON answer that must be stored in SQL. A test instead finds: Truncated JSON text enters database row. Which underlying issue best explains this finding?
- Context was flooded with low-relevance passages
- Retrieval uses only one of lexical or semantic signals
- Response wasn't parsed and schema validated
- Endpoint authentication or credential configuration is missing
Explanation
Correct Answer
C:Response wasn't parsed and schema validated. It accounts for the specific observed failure: truncated json text enters database row. The intended solution is validate and extract model json response before persistence with the required setup.
Incorrect Answers
A:Context was flooded with low-relevance passages. This concerns token cost spikes without improved grounding. Here, response wasn't parsed and schema validated.
B:Retrieval uses only one of lexical or semantic signals. This concerns one class of queries consistently misses important evidence. Here, response wasn't parsed and schema validated.
D:Endpoint authentication or credential configuration is missing. This concerns external rest call fails with unauthorized response. Here, response wasn't parsed and schema validated.
Question 957
An organization wants RAG that respects row-level security. Which database design or engineering approach most directly meets this requirement?
- Define prompt template with instructions and bounded evidence section
- Use groundedness, relevance and citation-based evaluation
- Run retrieval under requesting user's authorized context
- Use evidence-aware abstention in RAG prompting
Explanation
Correct Answer
C:Run retrieval under requesting user's authorized context. The implementation is apply rls predicate and per-document acl before prompt construction; success can be checked by compare retrieved source ids for different users. The method addresses the stated data and workload constraint.
Incorrect Answers
A:Define prompt template with instructions and bounded evidence section. This concerns a reusable prompt with SQL database retrieval. Instead, run retrieval under requesting user's authorized context.
B:Use groundedness, relevance and citation-based evaluation. This concerns checking whether rag helped over unguided prompts. Instead, run retrieval under requesting user's authorized context.
D:Use evidence-aware abstention in RAG prompting. This concerns not invent answer when SQL retrieval returns no supporting rows. Instead, run retrieval under requesting user's authorized context.
Question 958
An organization wants RAG that respects row-level security. The team selects: Run retrieval under requesting user's authorized context. Which implementation action puts this design into practice?
- Deduplicate by document ID and select newest approved version
- Configure audited redaction and role-based log access
- Build structured payload of question, context and citation IDs
- Apply RLS predicate and per-document ACL before prompt construction
Explanation
Correct Answer
D:Apply RLS predicate and per-document ACL before prompt construction. This is the concrete setup for run retrieval under requesting user's authorized context, and compare retrieved source ids for different users supplies a direct confirmation.
Incorrect Answers
A:Deduplicate by document ID and select newest approved version. This concerns a rag answer includes contradictory facts from old and new records. Instead, apply RLS predicate and per-document ACL before prompt construction.
B:Configure audited redaction and role-based log access. This is relevant when a compliance rag app cannot expose secrets in query logs. Instead, apply RLS predicate and per-document ACL before prompt construction.
C:Build structured payload of question, context and citation IDs. This concerns a reusable prompt with SQL database retrieval. Instead, apply RLS predicate and per-document ACL before prompt construction.
Question 959
An organization wants RAG that respects row-level security. After implementing the design, which check most directly validates the expected behavior?
- Compare retrieved source IDs for different users
- Open cited source and confirm effective date
- Compare hallucination rate and answer citation accuracy
- Test contradictory version pair yields current rule
Explanation
Correct Answer
A:Compare retrieved source IDs for different users. This verifies the requirement in the case rather than merely confirming that a job ran; an opposing result can reveal that rag pipeline bypasses sql authorization.
Incorrect Answers
B:Open cited source and confirm effective date. This concerns cite exact source version and timestamp. Instead, compare retrieved source IDs for different users.
C:Compare hallucination rate and answer citation accuracy. This concerns checking whether rag helped over unguided prompts. Instead, compare retrieved source IDs for different users.
D:Test contradictory version pair yields current rule. This concerns a rag answer includes contradictory facts from old and new records. Instead, compare retrieved source IDs for different users.
Question 960
An organization wants RAG that respects row-level security. A test instead finds: User sees facts from another tenant. Which underlying issue best explains this finding?
- Context was flooded with low-relevance passages
- No evaluated ground-truth and citation evidence exists
- Logging pipeline persists unredacted secrets
- RAG pipeline bypasses SQL authorization
Explanation
Correct Answer
D:RAG pipeline bypasses SQL authorization. It accounts for the specific observed failure: user sees facts from another tenant. The intended solution is run retrieval under requesting user's authorized context with the required setup.
Incorrect Answers
A:Context was flooded with low-relevance passages. This concerns token cost spikes without improved grounding. The relevant SQL or system operation is RAG pipeline bypasses SQL authorization.
B:No evaluated ground-truth and citation evidence exists. This concerns team declares success from fluent demos only. The relevant SQL or system operation is RAG pipeline bypasses SQL authorization.
C:Logging pipeline persists unredacted secrets. This concerns prompt history stores connection strings verbatim. The relevant SQL or system operation is RAG pipeline bypasses SQL authorization.
Developing AI-Enabled Database Solutions (DP-800) Practice Tests