The answer is Custom Question Answering, a feature within Azure AI Language that is the correct choice for building a self-service FAQ bot from policy documents. This feature uses a deep learning-based extractive reader to locate exact answer spans directly within PDFs and Word files, eliminating the need to manually create question-answer pairs. On the AI-900 exam, this scenario tests your understanding of how Custom Question Answering differs from pre-built FAQ solutions or traditional QnA Maker, which required manual pair creation. A common trap is confusing it with Conversational Language Understanding, but remember: CLU is for intent classification and entity extraction from user utterances, not for extracting answers from documents. For the exam, focus on the key phrase “extract answers directly from source documents” as your trigger for Custom Question Answering. Memory tip: think “Custom QA = Custom extraction from docs,” where the bot reads the policy files like a student skimming a textbook for the exact answer.
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
This AI-900 practice question tests your understanding of describe features of natural language processing workloads on azure. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A company wants to build a self-service FAQ bot that answers customer questions based on a collection of policy documents (PDFs and Word files). They want the bot to extract answers directly from the documents without manually creating question-answer pairs. Which Azure AI Language feature should they use?
Why wrong: Key Phrase Extraction identifies important concepts in text but does not support answering questions based on document content.
B
Conversational Language Understanding (CLU)
Why wrong: CLU is used for intent recognition and entity extraction in conversational contexts, not for extracting answers from documents.
C
Custom Question Answering
Custom Question Answering enables you to create a knowledge base from documents and automatically answer user questions using the content.
D
Azure OpenAI on your data
Why wrong: While Azure OpenAI can be used with your data, it is a generative AI service, not part of the core Azure AI Language NLP features. The question specifically asks for an Azure AI Language feature.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Custom Question Answering
Custom Question Answering (C) is the correct choice because it is specifically designed to extract answers directly from source documents (PDFs, Word files) without requiring manual creation of question-answer pairs. It uses a deep learning-based extractive reader to locate answer spans within the text, making it ideal for building a self-service FAQ bot from policy documents.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Key Phrase Extraction
Why it's wrong here
Key Phrase Extraction identifies important concepts in text but does not support answering questions based on document content.
✗
Conversational Language Understanding (CLU)
Why it's wrong here
CLU is used for intent recognition and entity extraction in conversational contexts, not for extracting answers from documents.
✓
Custom Question Answering
Why this is correct
Custom Question Answering enables you to create a knowledge base from documents and automatically answer user questions using the content.
Related concept
Read the scenario before looking for a memorised answer.
✗
Azure OpenAI on your data
Why it's wrong here
While Azure OpenAI can be used with your data, it is a generative AI service, not part of the core Azure AI Language NLP features. The question specifically asks for an Azure AI Language feature.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse Custom Question Answering with Conversational Language Understanding (CLU) because both involve 'language understanding,' but CLU requires manual intent/entity creation and does not extract answers from documents, while Custom Question Answering is purpose-built for extractive QA from uploaded files.
Trap categories for this question
Keyword trap
Key Phrase Extraction identifies important concepts in text but does not support answering questions based on document content.
Detailed technical explanation
How to think about this question
Custom Question Answering (formerly QnA Maker) uses a two-stage pipeline: first, a ranker retrieves top candidate passages from the indexed documents using TF-IDF and semantic similarity; second, a BERT-based extractive reader identifies the exact answer span within the passage. This ensures that answers are directly quoted from the source, which is critical for compliance-heavy policy documents where verbatim accuracy is required. The service also supports active learning, where user queries can be used to suggest new question-answer pairs for manual review.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
Related glossary terms
Concepts from this question explained
These glossary pages explain the core terms tested in this AI-900 question in full detail.
Describe features of Natural Language Processing workloads on Azure — This question tests Describe features of Natural Language Processing workloads on Azure — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Custom Question Answering — Custom Question Answering (C) is the correct choice because it is specifically designed to extract answers directly from source documents (PDFs, Word files) without requiring manual creation of question-answer pairs. It uses a deep learning-based extractive reader to locate answer spans within the text, making it ideal for building a self-service FAQ bot from policy documents.
What should I do if I get this AI-900 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. What is 'question answering' in Azure AI Language and what are its two main types?
medium
A.Multiple-choice question generation and open-ended answer scoring
✓ B.Custom QA (trained on your documents) and prebuilt QA (document provided at query time)
C.Structured QA for databases and unstructured QA for text documents
D.Real-time QA for chatbots and batch QA for scheduled document processing
Why B: Option B is correct because Azure AI Language's 'question answering' feature provides two distinct capabilities: Custom QA, where you train a model on your own documents (e.g., PDFs, FAQs) to answer questions from that knowledge base, and Prebuilt QA, which uses a document provided at query time to extract answers without prior training. This distinction is fundamental to how the service is deployed—either as a persistent, trained knowledge base or as an on-the-fly extraction from a user-supplied document.
Last reviewed: Jun 11, 2026
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This AI-900 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-900 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.