AI-900 Practice Test 45 — 15 Questions

Question 1

A hospital uses an AI system to analyze patient records for research. To protect patient identities, the system should not store or transmit any personally identifiable information (PII) outside the secure network. Which responsible AI principle is most directly addressed by this requirement?

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

Accepted Answer

Privacy and Security. The requirement to not store or transmit PII outside the secure network directly addresses the Privacy and Security principle. This principle ensures that individuals' data is protected from unauthorized access or exposure, which is critical in healthcare AI systems handling sensitive patient records. By restricting PII to the secure network, the system upholds data confidentiality and compliance with regulations like HIPAA.

Answer

Fairness

Answer

Inclusiveness

Answer

Reliability and Safety

Question 2

A legal firm needs to process thousands of contracts to automatically identify important terms such as dates, monetary amounts, names of parties, and legal citations. Which built-in feature of the Azure AI Language service is best suited for this task?

Accepted Answer

C) Entity Recognition. Entity Recognition (also called Named Entity Recognition, NER) is the correct choice because it is specifically designed to identify and categorize predefined entities such as dates, monetary amounts, person names, organizations, and legal citations from unstructured text. The Azure AI Language service's NER capability can automatically extract these important terms from thousands of contracts, making it the ideal built-in feature for this task.

Answer

A) Sentiment Analysis

Answer

B) Key Phrase Extraction

Answer

D) Language Detection

Question 3

What information does Azure AI Face service provide about detected faces beyond just their location?

Accepted Answer

Age estimate, emotion, head pose, and other facial attributes. Azure AI Face service can extract a wide range of facial attributes beyond just the bounding box coordinates. These include age estimate, emotion (e.g., happiness, sadness, surprise), head pose (pitch, yaw, roll), facial hair, glasses, and more, making option B correct.

Answer

Only the coordinates of the face bounding box

Answer

The person's name and identity from a public database

Answer

Only whether the face belongs to a human or not

Question 4

A company deploys an AI chatbot on its website to answer customer questions. The company wants to be transparent about the nature of the interaction. Which Microsoft responsible AI principle is most directly relevant to ensuring users know they are communicating with an AI and not a human?

Accepted Answer

Transparency. Transparency is the Microsoft responsible AI principle that requires AI systems to be designed so that users are aware they are interacting with an AI, not a human. In the context of a chatbot, this means clearly disclosing the AI nature of the system, such as through a label or introductory message, to avoid deception and build trust.

Answer

Inclusiveness

Answer

Privacy and security

Answer

Accountability

Question 5

What are the 'six pillars' of Microsoft's Responsible AI framework?

Accepted Answer

Fairness, Reliability & Safety, Privacy & Security, Inclusiveness, Transparency, Accountability. Microsoft's Responsible AI framework is built on six core principles: Fairness, Reliability & Safety, Privacy & Security, Inclusiveness, Transparency, and Accountability. These pillars guide the ethical development and deployment of AI systems, ensuring they are trustworthy and aligned with human values. The other options describe general IT or business metrics, not the specific ethical framework Microsoft mandates for AI workloads.

Answer

Speed, Accuracy, Cost, Scalability, Security, Compliance

Answer

Innovation, Efficiency, Quality, Agility, Trust, Sustainability

Answer

Openness, Collaboration, Transparency, Community, Excellence, Impact

Question 6

A developer uses Azure OpenAI Service to generate product name suggestions. They want to ensure the model never outputs a specific word, such as 'Corporation', because it is too formal for their brand. Which parameter should the developer configure to reduce the probability of that token being generated?

Accepted Answer

Logit Bias. Logit Bias is the correct parameter because it directly modifies the logits (raw prediction scores) for specific tokens before the softmax function, allowing the developer to reduce the probability of generating a particular token like 'Corporation'. By setting a negative bias value for that token's ID, the model is less likely to output it, even if it would otherwise be a high-probability choice. This is the only parameter that provides token-level control over output content.

Answer

Temperature

Answer

Top P (Nucleus Sampling)

Answer

Frequency Penalty

Question 7

A legal firm needs to automatically extract the names of organizations and monetary values from thousands of legal contracts. They want to use a prebuilt Azure AI Language feature without custom training. Which feature should they use?

Accepted Answer

Named entity recognition. Named entity recognition (NER) is the correct choice because it is specifically designed to identify and categorize entities such as organization names and monetary values from unstructured text. Azure AI Language's prebuilt NER model can extract these entity types without any custom training, making it ideal for processing legal contracts at scale.

Answer

Key phrase extraction

Answer

Sentiment analysis

Answer

Text summarization

Question 8

What is 'retrieval-augmented generation' (RAG) and what problem does it solve?

Accepted Answer

Retrieving relevant documents from a knowledge base to provide accurate context for LLM responses. Retrieval-augmented generation (RAG) combines a retrieval step with a generative language model. It first retrieves relevant documents or passages from an external knowledge base (e.g., Azure Cognitive Search) and then feeds that context into the LLM to ground its response. This solves the problem of LLMs producing outdated, hallucinated, or factually incorrect answers by ensuring the model has access to current, authoritative information.

Answer

Storing model responses in a cache to retrieve them faster for repeated questions

Answer

Generating random responses and selecting the most relevant using a ranker model

Answer

A technique for making LLM responses shorter by removing irrelevant sections

Question 9

What is 'Azure Language Studio' and what can you do with it?

Accepted Answer

A no-code web portal for testing and training Azure AI Language capabilities. Azure Language Studio is a no-code web portal that allows users to explore, test, and train Azure AI Language capabilities without writing code. It provides a graphical interface for tasks like sentiment analysis, key phrase extraction, and custom text classification, making it accessible for non-developers to build and evaluate NLP models.

Answer

A code editor for writing Python NLP scripts connected to Azure AI Language APIs

Answer

A service for hosting and running multi-language web applications in Azure

Answer

A creative writing studio application powered by AI language generation

Question 10

A healthcare organization is developing an AI system to recommend treatment plans for patients based on their medical history. According to Microsoft's responsible AI principles, which principle is most directly concerned with ensuring that the system protects patients' health data from unauthorized access or misuse?

Accepted Answer

Privacy and security. The Privacy and security principle is most directly concerned with protecting patients' health data from unauthorized access or misuse. In this scenario, the AI system must comply with regulations like HIPAA and GDPR, ensuring data encryption, access controls, and audit logs are in place to safeguard sensitive medical information.

Answer

Transparency

Answer

Fairness

Answer

Reliability and safety

Question 11

What is the 'Phi' family of models in Azure AI Foundry and what makes them distinctive?

Accepted Answer

Microsoft's small language models that achieve high capability at much smaller parameter counts. The Phi family consists of small language models (SLMs) developed by Microsoft that achieve high performance on reasoning and language tasks despite having significantly fewer parameters than large models like GPT-4. Their distinctive design uses high-quality training data and novel scaling techniques to deliver competitive capability with lower computational cost, making them ideal for resource-constrained environments and real-time applications.

Answer

Large models from OpenAI that provide the highest capability for complex tasks

Answer

Models specifically designed for processing and analysing structured financial data

Answer

A family of image generation models competing with DALL-E for artistic content creation

Question 12

A home security system uses a camera to detect common household objects such as a person, a pet, a bag, or a package. The system needs to identify the presence and location (bounding box) of these objects in images. The development team wants to use a prebuilt Azure AI service without any custom training. Which Azure Computer Vision capability should they use?

Accepted Answer

Image Analysis – Object Detection. (Image Analysis – Object Detection) is correct because the requirement is to identify both the presence and location (bounding box) of common household objects in images using a prebuilt Azure AI service without custom training. Azure Computer Vision's Image Analysis – Object Detection provides pre-trained models that can detect multiple objects, including people, pets, bags, and packages, and return their bounding box coordinates, exactly matching the scenario.

Answer

Optical Character Recognition (OCR)

Answer

Image Analysis – Image Captioning

Answer

Custom Vision

Question 13

A global e-commerce company receives product reviews in multiple languages. They want to automatically identify the language of each review to route it to the appropriate translation queue. Which Azure AI Language feature should they use?

Accepted Answer

Language Detection. Language Detection is the correct Azure AI Language feature because it is specifically designed to identify the language of a given text input, returning a language name and a confidence score. This directly meets the requirement to automatically detect the language of product reviews so they can be routed to the appropriate translation queue.

Answer

Sentiment Analysis

Answer

Key Phrase Extraction

Answer

Entity Recognition

Question 14

A company wants to use Azure OpenAI to generate product descriptions. They have a few example descriptions that perfectly match their desired style and structure. They want the model to produce new descriptions in the same style without retraining the underlying model. Which approach should they use?

Accepted Answer

Few-shot prompting with the examples in the prompt. Few-shot prompting provides the model with a small number of example inputs and outputs directly in the prompt, allowing it to infer the desired style and structure without any training. This approach is ideal when you have a few high-quality examples and want to generate new content that matches them, without the cost and complexity of fine-tuning.

Answer

Fine-tune the model on the example descriptions

Answer

Embeddings and similarity search

Answer

Content filtering configurations

Question 15

What is 'transfer learning' and how is it different from training from scratch?

Accepted Answer

Transfer learning fine-tunes a pre-trained model on a new task — requiring far less data and compute than training from scratch. Transfer learning starts with a model already trained on a large dataset (e.g., ImageNet) and fine-tunes it on a smaller, task-specific dataset. This approach requires significantly less data and computational resources compared to training from scratch, where all model weights are randomly initialized and learned from the ground up. It is especially effective when the new task is similar to the original training task, allowing the pre-trained features to be reused.

Answer

Transfer learning and training from scratch produce identical results

Answer

Transfer learning copies model weights between Azure subscriptions

Answer

Transfer learning is used only when the original training data is unavailable