AI-102 Implement generative AI solutions Practice Question
A legal team wants an assistant that drafts contract summaries. Their policy requires that every generated summary include traceable references to the exact clauses used and that reviewers be able to see which source passages informed each statement. You are using Azure OpenAI with your own document index. Which approach best meets the traceability requirement?
⚠ Common exam trap
Candidates often confuse model confidence signals such as logprobs with source attribution, when only retrieved citation metadata can identify the clause behind a statement.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use the On Your Data pattern with Azure AI Search, return document chunks with their IDs and titles, and instruct the model to cite the retrieved chunk identifiers in its output.
Traceability requires linking generated text back to specific source passages. Using Azure AI Search as the grounding source with the On Your Data pattern returns citation metadata for the retrieved chunks, and prompting the model to cite those chunks produces summaries where each statement can be traced to a clause. Quota, fine-tuning, and logprobs do not create that link.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Fine-tune the base model on previously approved contract summaries so its style matches legal expectations.
Why it's wrong here
Fine-tuning adapts tone and format but does not attach source references to generated text, and it cannot guarantee that a clause used in training is the same one present in a new contract. It also risks memorizing outdated language, so it fails the requirement that each summary be traceable to the actual clauses in the document being reviewed.
- ✗
Enable the model's logprobs parameter and expose the token probabilities to reviewers as evidence of reliability.
Why it's wrong here
Token probabilities indicate how confident the model was in its word choices, not which source passage supported a statement. A high-probability sentence can still be fabricated or drawn from the wrong clause, so logprobs give reviewers a misleading signal and do not provide the clause-level traceability the policy demands.
- ✗
Increase the model deployment's tokens-per-minute quota so longer contracts fit in a single prompt.
Why it's wrong here
Quota controls throughput, not provenance. Raising tokens per minute may let a bigger prompt through, but without a citation mechanism the summary will not point back to specific clauses, so reviewers still cannot verify which passage supported each statement. Throughput tuning does not satisfy a traceability policy.
- ✓
Use the On Your Data pattern with Azure AI Search, return document chunks with their IDs and titles, and instruct the model to cite the retrieved chunk identifiers in its output.
Why this is correct
Grounding the completion in Azure AI Search chunks and returning citations lets the model reference the exact retrieved passages, and the service can return the citation metadata alongside the response. Reviewers can then map each statement to a chunk and its source clause, which directly satisfies the traceability policy without retraining.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.