AI-900 Practice Test 30 — 15 Questions

Question 1

A developer is using Azure OpenAI Service to generate structured data in JSON format. They want to ensure that every response is valid JSON without adding instructions in every prompt. Which Azure OpenAI feature should they configure?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Set the response_format parameter to 'json_object'.. Azure OpenAI Service provides a `response_format` parameter that can be set to `json_object`, which instructs the model to always return valid JSON output. This ensures structured data without requiring the developer to include formatting instructions in every prompt, as the service enforces JSON schema compliance at the API level.

Answer

Set the temperature parameter to a low value (e.g., 0).

Answer

Set the top_p parameter to a high value (e.g., 1).

Answer

Set the max_tokens parameter to a high value (e.g., 2000).

Question 2

What is 'Azure Machine Learning pipelines' and why are they used?

Accepted Answer

Reusable orchestrated workflows that automate and version-control the full ML training lifecycle. Azure Machine Learning pipelines are reusable orchestrated workflows that automate and version-control the full ML training lifecycle, including data preparation, training, evaluation, and deployment. They enable reproducibility, parallel execution of steps, and easy sharing across teams, which is why option B is correct.

Answer

Network pipelines for transferring data between Azure regions at high speed

Answer

CI/CD pipelines in Azure DevOps for deploying application code to production

Answer

Data pipelines that ingest streaming data from IoT sensors into Azure storage

Question 3

What is 'text generation' as a generative AI capability and what are common use cases?

Accepted Answer

Creating new coherent text from prompts for writing, code, summaries, and conversational AI. Text generation in generative AI refers to the capability of models (like GPT-4 or GPT-3.5) to produce new, coherent text based on a given prompt. This includes tasks such as writing articles, generating code, creating summaries, and powering conversational AI agents. The key distinction is that the output is novel content, not a direct extraction or transformation of existing text.

Answer

Extracting and copying text from scanned images using OCR

Answer

Converting speech audio into a written transcript

Answer

Formatting existing text by adding headings, bullets, and correct punctuation

Question 4

A legal firm needs to automatically sort incoming legal documents into predefined categories such as 'Contract', 'Brief', 'Motion', and 'Discovery'. They have a set of 500 manually labeled documents to use as examples. Which Azure AI Language feature should they use to build this classification system?

Accepted Answer

Custom text classification. Custom text classification is the correct choice because it allows the legal firm to train a model using their 500 labeled documents to classify text into predefined categories like 'Contract', 'Brief', 'Motion', and 'Discovery'. This feature enables supervised learning where the model learns from labeled examples to automatically sort incoming documents, which is exactly the requirement described.

Answer

Key phrase extraction

Answer

Named entity recognition

Answer

Sentiment analysis

Question 5

A bank uses an AI system to approve or deny personal loan applications. Several customers whose loans were denied have asked for an explanation of why their application was rejected. Which Microsoft responsible AI principle requires the bank to provide understandable reasons for the AI's decision?

Accepted Answer

Transparency. Transparency is the Microsoft responsible AI principle that requires AI systems to be understandable and interpretable. In this scenario, the bank must provide clear, understandable reasons for loan denials, which directly aligns with transparency's goal of enabling users to understand how and why decisions are made. This principle ensures that AI outcomes are not opaque black-box decisions but can be explained in human terms.

Answer

Reliability and safety

Answer

Fairness

Answer

Privacy and security

Question 6

What is feature engineering in machine learning?

Accepted Answer

Selecting, transforming, and creating input variables from raw data to improve model performance. Feature engineering is the process of selecting, transforming, and creating input variables (features) from raw data to improve the performance of machine learning models. This step is critical because the quality and relevance of features directly impact a model's ability to learn patterns and generalize to new data. In Azure Machine Learning, feature engineering is often performed using tools like the 'Feature Engineering' step in automated ML or custom Python scripts with libraries such as pandas and scikit-learn.

Answer

Designing the hardware chips for running ML models

Answer

Selecting which neural network layers to include in a model

Answer

Writing code to deploy ML models as REST APIs

Question 7

A digital art library wants to automatically generate a list of relevant keywords (e.g., 'landscape', 'portrait', 'abstract', 'nature') for each image in their collection. Which Azure Computer Vision capability should they use?

Accepted Answer

Image Tagging. Image Tagging (B) is the correct capability because it analyzes the content of an image and returns a set of relevant keywords (tags) based on the detected objects, scenes, and concepts. This directly matches the requirement to generate a list of keywords like 'landscape', 'portrait', 'abstract', and 'nature' for each image.

Answer

Optical Character Recognition (OCR)

Answer

Image Captioning

Answer

Object Detection

Question 8

A bank uses an AI system to approve loan applications. The bank wants to ensure that applicants can understand why a loan was approved or rejected. Which Microsoft responsible AI principle is most directly relevant to this requirement?

Accepted Answer

Transparency. The requirement that applicants can understand why a loan was approved or rejected directly aligns with the Transparency principle, which mandates that AI systems be interpretable and that decisions be explainable to users. In this context, the bank must provide clear reasoning for loan outcomes, enabling applicants to comprehend the factors influencing the decision, such as credit score thresholds or income verification rules.

Answer

Fairness

Answer

Inclusiveness

Answer

Reliability and Safety

Question 9

What is prompt injection and why is it a security concern for AI systems?

Accepted Answer

A security attack where malicious inputs try to override AI system instructions or bypass guardrails. Prompt injection is a security attack where a malicious user crafts input that overrides the AI system's original instructions or bypasses its guardrails, causing the model to behave in unintended ways. This is a critical security concern because it can lead to data exfiltration, unauthorized actions, or the generation of harmful content, undermining the trust and safety of AI deployments.

Answer

A technique for making AI prompts shorter and more efficient

Answer

The process of adding examples to prompts to improve model performance

Answer

A method of injecting training data into a model after deployment

Question 10

What is transfer learning and how does it apply to NLP models?

Accepted Answer

Using knowledge from a large pre-trained model as the starting point for learning a new, related task. Transfer learning in NLP involves taking a large pre-trained model (like BERT or GPT) that has been trained on a massive corpus and fine-tuning it on a smaller, task-specific dataset. This approach dramatically reduces the amount of labeled data and training time needed, while leveraging the linguistic knowledge already captured by the base model. In Azure, services like Azure Cognitive Service for Language use transfer learning to provide high-accuracy custom models with minimal training data.

Answer

Moving a trained model from one Azure region to another for deployment

Answer

Transferring labeled training data between different ML projects

Answer

Automatically translating ML models from Python to other programming languages

Question 11

What is 'text-to-speech' (TTS) in Azure AI Speech?

Accepted Answer

Converting written text into synthesised spoken audio. Text-to-speech (TTS) in Azure AI Speech converts written text into natural-sounding synthesized spoken audio. It uses deep neural networks to generate human-like speech from input text, enabling applications like voice assistants and audiobook narration.

Answer

Extracting text from speech audio recordings

Answer

Translating spoken text from one language to another in real time

Answer

Detecting the emotional tone of speech audio to classify speaker sentiment

Question 12

What is the purpose of Azure AI Speech's speaker recognition feature?

Accepted Answer

To identify who is speaking based on their unique voice characteristics. Azure AI Speech's speaker recognition feature is designed to identify and verify individuals based on their unique vocal characteristics, such as pitch, tone, and speech patterns. This is achieved through voice biometrics, where the service creates a unique voiceprint for each speaker and matches it against enrolled profiles. Option B correctly captures this purpose, distinguishing it from transcription or audio processing tasks.

Answer

To transcribe spoken audio into text

Answer

To detect whether audio contains speech or background noise

Answer

To improve audio quality by removing background noise

Question 13

A social media company uses Azure OpenAI Service to automatically generate captions for user-uploaded images. The company has a strict content policy that prohibits any generated captions containing profanity, hate speech, or self-harm references. Which feature of the Azure OpenAI Service should the company configure to automatically block such harmful content?

Accepted Answer

Content filtering. Content filtering is the correct feature because it is specifically designed to detect and block harmful content such as profanity, hate speech, and self-harm references in both input prompts and generated outputs. Azure OpenAI Service's content filtering system uses multi-class classification models to enforce responsible AI policies automatically, without requiring custom training or manual moderation.

Answer

Temperature parameter

Answer

Top-p parameter

Answer

Max-tokens parameter

Question 14

What is 'Azure AI Vision's landmark detection' and what does it return?

Accepted Answer

Identifying well-known physical landmarks (Eiffel Tower, Big Ben) in photographs with a confidence score. Azure AI Vision's landmark detection is a pre-built computer vision capability that identifies well-known physical landmarks (e.g., Eiffel Tower, Big Ben) in images. It returns the landmark name along with a confidence score indicating the likelihood of the match, enabling applications like automated photo tagging or travel content enrichment.

Answer

Detecting important milestones in a project timeline using AI

Answer

Creating highlighted markers on maps showing user-defined points of interest

Answer

Detecting major architectural features of any building regardless of whether it is famous

Question 15

What is 'batch document translation' in Azure AI Translator and what file formats does it support?

Accepted Answer

Asynchronous translation of Word, PDF, Excel, and HTML documents preserving their layout. Azure AI Translator's batch document translation is an asynchronous operation that translates entire documents (such as Word, PDF, Excel, and HTML) while preserving their original layout and structure. This is distinct from real-time or synchronous translation, as batch translation processes files in bulk via a job-based API, making it ideal for large-scale or non-interactive scenarios.

Answer

Translating database records in batches by sending SQL queries to the translation API

Answer

Translating phone call transcripts in batches after calls are completed

Answer

A real-time API that translates one document page at a time as users scroll