AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Which THREE components are required to build a custom skill for Azure AI Search enrichment?
⚠ Common exam trap
Candidates often think a custom skill requires an orchestration tool like Power Automate or a persistent storage layer, but Azure AI Search's enrichment pipeline handles orchestration natively and only needs a stateless HTTPS endpoint with a defined JSON schema.
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
✓
A web API endpoint that accepts JSON input and returns JSON output.
To build a custom skill for Azure AI Search enrichment, you must expose your logic through a web API endpoint that accepts JSON input and returns JSON output (C), because the skillset invokes the skill via an HTTP POST with a JSON payload and expects a JSON response. The endpoint must be secured with HTTPS (D), since Azure AI Search requires custom skill connections to use HTTPS for secure transport. You also need a JSON schema defining inputs and outputs (E), which describes the expected input fields and output fields so the skillset can map enriched document content correctly. A database for intermediate results (A) is not required, as the skillset pipeline passes data between skills in memory, and a Power Automate flow (B) is not a supported orchestration mechanism for custom skills.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A database to store intermediate results.
Why it's wrong here
A custom skill is a web API endpoint (Azure Function or similar) accepting and returning enriched documents; it needs no intermediate database. It is tempting because enrichment pipelines can persist state, but the skill contract itself is stateless request and response.
- ✗
A Power Automate flow to orchestrate the skill.
Why it's wrong here
A custom skill is invoked directly by the skillset through its web API endpoint; Power Automate is not part of the enrichment pipeline. It is tempting because Power Automate orchestrates many Azure workflows, but skillset execution is handled by the Azure AI Search service itself.
- ✓
A web API endpoint that accepts JSON input and returns JSON output.
Why this is correct
A custom skill is invoked by the enrichment pipeline as a web API call, so it must expose an endpoint accepting a JSON request body and returning a JSON response containing the enriched values the skillset consumes.
- ✓
An HTTPS endpoint for the API.
Why this is correct
A custom skill must expose its logic through a publicly reachable HTTPS endpoint, since the Azure AI Search enrichment pipeline calls it over the web during skillset execution. This satisfies the connectivity requirement: the service invokes your API directly, so a secure, internet-accessible URL is mandatory.
- ✓
A JSON schema defining inputs and outputs.
Why this is correct
A custom skill requires a JSON schema specifying the `@odata.type`, `name`, `description`, `context`, and `inputs`/`outputs` mappings, which Azure AI Search uses to bind enrichment pipeline data. This schema satisfies the interface contract constraint, enabling the skillset to pass values between the custom skill and the indexer.
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 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.