Courseiva

AI-102 Practice Question: Implement natural language processing solutions

Your Azure AI Language custom question answering project answers product questions from a knowledge base. Users report that the bot returns the same generic answer regardless of how they phrase a question, even when the knowledge base contains the correct information. You need to diagnose why the model is not matching semantically similar user phrasings to the right answer. What should you do first?

⚠ Common exam trap

The trap here is jumping to content fixes like alternate questions or more documents when the uniform generic answer is a strong signal of a default-answer fallback or a stale deployment target.

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

✓

Review the project's default answer and confirm the deployed model is the one being queried by the bot

When every phrasing produces the same generic response, the runtime is almost certainly falling back to the project's default answer, which occurs when no question-answer pair scores above the threshold or when the bot queries a deployment that lacks the trained model. Inspecting the default answer and verifying the deployment target isolates configuration problems before any content changes are made. Content remedies such as alternate questions or more documents address different symptoms.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • ✗

    Enable active learning and wait for the model to retrain automatically on user queries

    Why it's wrong here

    Active learning surfaces suggested alternate questions from real traffic, but it does not automatically retrain or fix a deployment mismatch. If the bot is hitting the wrong deployment or the default answer threshold is misconfigured, active learning suggestions never reach users. It is a long-term accuracy improvement, not a diagnostic step, so it cannot explain the identical generic answer.

  • ✗

    Add alternate questions to each question-answer pair in the project

    Why it's wrong here

    Alternate questions improve recall for specific phrasings, but they are a content remedy rather than a diagnosis. If the bot returns the same generic answer for every phrasing, the underlying issue may be configuration or deployment, not missing phrasings. Adding alternates before identifying the cause wastes effort and may mask the real problem, so it is not the correct first diagnostic step.

  • ✓

    Review the project's default answer and confirm the deployed model is the one being queried by the bot

    Why this is correct

    A generic answer returned for every query strongly suggests the runtime is falling back to the default answer, which happens when no question-answer pair meets the confidence threshold or when the bot queries a stale or empty deployment. Verifying the default answer text and confirming the bot targets the correct deployed model version is the fastest way to isolate a configuration or deployment mismatch before changing content.

  • ✗

    Increase the number of documents in the knowledge base and re-index the project

    Why it's wrong here

    Adding documents expands coverage but does nothing to explain why every phrasing yields the same generic answer. The symptom points to a fallback or deployment issue, not missing content. Re-indexing an already populated knowledge base consumes time and may temporarily disrupt the project while leaving the actual cause, such as an incorrect deployment target or low confidence threshold, unaddressed.

About these practice questions

This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

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.