AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
You are building an Azure AI Search solution that uses a custom skill to enrich documents. The custom skill is implemented as an Azure Function. You need to ensure that the custom skill can access the documents' content and output enriched data. Which two actions should you perform? (Choose two.)
⚠ Common exam trap
The trap here is focusing on security or performance settings like managed identity or batch size, which are not required for basic functionality of a custom skill.
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
✓
Ensure the Azure Function accepts a JSON payload with the expected input and returns a JSON response.
The custom skill must be defined in the skillset with proper input and output mappings to integrate with the enrichment pipeline. Additionally, the Azure Function must handle the JSON payload correctly. These two actions ensure the skill can access document content and return enriched data for indexing.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Add the Azure Function's output to the index's field mappings.
Why it's wrong here
Output from a custom skill is placed in the enrichment tree, and then index field mappings map enriched fields to index fields. Directly adding the function's output to index field mappings without defining it in the skillset's output mappings would not work, as the enrichment tree must be populated first.
- ✓
Ensure the Azure Function accepts a JSON payload with the expected input and returns a JSON response.
Why this is correct
Azure AI Search sends a JSON payload containing the input values to the custom skill and expects a JSON response with the output values. The Azure Function must be implemented to parse the request and return the appropriate structure, otherwise the skill will fail or produce no output.
- ✗
Set the custom skill's batch size to 1 to ensure sequential processing.
Why it's wrong here
Batch size controls how many documents are sent to the skill in one request. Setting it to 1 may reduce throughput and is not required for the skill to access content or output data. It is a performance tuning parameter, not a functional necessity for the enrichment process.
- ✗
Configure the indexer to use a managed identity to access the Azure Function.
Why it's wrong here
While managed identity can be used for secure access to the Azure Function, it is not strictly required for the custom skill to function. The skill can be accessed via an HTTP endpoint with a key. This action addresses security, not the core requirement of input/output handling.
- ✓
Define the custom skill in the skillset with the correct input source and output mappings.
Why this is correct
The skillset definition specifies how the custom skill receives input from the enrichment tree and where its output is placed. Without correct input and output mappings, the skill cannot access document content or contribute enriched data to the index, making this action essential.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.