Question 652 of 945
AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
A company uses Azure Cognitive Search to index customer support emails. They need to implement a custom skill that extracts the sentiment of the email body and also identifies the primary product mentioned. The custom skill is a Python function deployed as an Azure Function. They want to ensure the skill can process multiple documents concurrently and handle errors gracefully. Which THREE configurations should they apply?
⚠ Common exam trap
A common mix-up: candidates confuse the 'context' property with the 'inputs' property, incorrectly assuming that setting context to '/document/pages/*' is necessary for page-level processing, when in fact the context should match the granularity at which the skill should operate—here, the entire document for overall sentiment.
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
✓
Set the inputs of the skill to include the 'text' field from the enriched document and the 'product' field from a previous skill.
The custom skill must receive the email body text for sentiment analysis and the product field from a prior skill (e.g., a key phrase extraction or entity recognition skill) to identify the primary product. This ensures the Azure Function has all required inputs to produce the desired outputs (sentiment score and product name).
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Set continueOnError to false to ensure that if the skill fails for one document, the entire indexer run stops.
Why it's wrong here
Setting continueOnError to false would cause the entire run to fail; it's better to set it to true to skip failures for individual documents.
- ✓
Set the inputs of the skill to include the 'text' field from the enriched document and the 'product' field from a previous skill.
Why this is correct
Inputs define the data passed to the skill; they should reference fields from the enrichment pipeline.
- ✓
Set the uri of the skill to the HTTP endpoint of the Azure Function, including the function key.
Why this is correct
Custom skills must point to the function's endpoint; Azure Functions are typically accessed via an HTTP URL with a code or key.
- ✗
Set the context property to '/document/pages/*' to process each page of the email individually.
Why it's wrong here
Emails are not paginated; setting context to '/document' is appropriate to process the entire document.
- ✓
Set the batchSize of the custom skill definition to 10 to allow parallel processing of multiple documents.
Why this is correct
A higher batchSize allows the indexer to send multiple documents per skill invocation, improving throughput.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 11, 2026
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.