AI-102 Plan and manage an Azure AI solution Practice Question
Your Azure AI Search solution uses a custom skill to call an external API. The skill runs locally but fails when deployed to the search service. What is the most likely cause?
⚠ Common exam trap
Many candidates assume the skill logic is faulty (input/output mappings) rather than recognizing that the network connectivity and HTTPS requirement is the fundamental difference between local testing and cloud execution.
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
✓
The skill endpoint is not publicly accessible via HTTPS.
When a custom skill runs locally but fails after deployment to Azure AI Search, the most common cause is that the skill's endpoint is not publicly accessible via HTTPS. Azure AI Search indexers execute skills in the cloud and must be able to reach the external API over the internet using a secure HTTPS connection; localhost or HTTP endpoints will fail.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The skill's output field mappings are missing.
Why it's wrong here
Missing output field mappings would drop enriched values from the index, but the skill itself would still execute and call the API. Output mappings are configured when you want skill output written into a specific index field, so they are the right focus when results appear but land nowhere.
- ✗
The skill's input field mappings are incorrect.
Why it's wrong here
Incorrect input field mappings would pass wrong or empty values into the skill, yet the external API call would still fire and the skill would run. Input mappings are what you correct when the skill executes but receives the wrong source content from the enrichment tree.
- ✗
The indexer name is misspelled in the skillset.
Why it's wrong here
A misspelled indexer name would prevent the indexer from being created or run at all, not cause a deployed skill to fail only at runtime. Indexer naming matters when you are authoring or referencing the indexer definition itself, not when a working pipeline's custom skill breaks.
- ✓
The skill endpoint is not publicly accessible via HTTPS.
Why this is correct
Custom skills execute server-side within Azure AI Search, so the external API must be reachable over public HTTPS; localhost or private endpoints work locally but fail once deployed. This satisfies the stem's deployment constraint, where the skill's endpoint becomes unreachable from the search service's network context.
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 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.