AI-102 Plan and manage an Azure AI solution Practice Question
You are planning an Azure AI solution that uses Azure AI Search with semantic ranker and a custom skill. The solution must meet the following requirements: - Process documents in multiple languages (English, Spanish, French). - Use a custom skill to extract entities via an Azure Function. - Ensure that the indexer can resume from failures. Which TWO actions should you include in your plan?
⚠ Common exam trap
Test-takers frequently confuse 'maxFailedItems' with a resume mechanism, but it only controls the tolerance for failures during a single run, not the ability to resume after a failure; the correct approach is to combine a change detection policy with 'failOnUnprocessedDocuments' set to false.
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
✓
Generate a data change detection policy on the data source.
A data change detection policy (e.g., HighWaterMarkChangeDetectionPolicy or SqlIntegratedChangeTrackingPolicy) enables the indexer to track which documents have been modified or added. This allows the indexer to resume from failures by reprocessing only the changed or unprocessed documents, rather than starting over from scratch. Without this policy, a failure would require a full reindex, which is inefficient and violates the requirement to resume from failures.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Generate a data change detection policy on the data source.
Why this is correct
A change detection policy allows the indexer to identify new/modified documents and resume from the last successful checkpoint.
- ✗
Configure separate indexer data sources for each language.
Why it's wrong here
The semantic ranker supports multiple languages in a single indexer; separate data sources are not required.
- ✓
Set the indexer property 'failOnUnprocessedDocuments' to false.
Why this is correct
This allows the indexer to skip documents that cause failures and continue processing, enabling resumption.
- ✗
Set the indexer property 'maxFailedItems' to a high value.
Why it's wrong here
This controls the number of failures before the indexer stops, but does not enable resumption.
- ✗
Enable Azure Monitor logs for the indexer to track failures.
Why it's wrong here
Indexer history is automatically available in the portal; Azure Monitor is not needed for resumption.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 945 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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.