Ditch the Recycled Junk: Master the AI-900 Exam with Confidence

According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module “Extract insights from text with the Text Analytics service”, key phrase extraction is a feature of the Text Analytics service that identifies the most important words or phrases in a given document. It helps summarize the main ideas by isolating significant concepts or terms that describe what the text is about.

In this scenario, the goal is to determine which documents share similar topics or themes. By extracting key phrases from each document (for example, “policy renewal,” “coverage limits,” “claim process”), you can compare and categorize documents based on overlapping keywords. This is exactly how key phrase extraction is used—to summarize and group text content by topic relevance.

The other options do not fit this use case:

A. Translation uses the Translator service, not key phrase extraction.

B. Generating video captions involves speech recognition and computer vision.

C. Identifying sentiment relates to sentiment analysis, not key phrase extraction.

According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module “Identify features of computer vision workloads on Azure”, computer vision models can perform different types of image analysis depending on the goal of the task. The main types include image classification, object detection, and semantic segmentation. Each method analyzes images at a different level of granularity.

Image Classification → Separate images of polar bears and brown bearsImage classification assigns an entire image to a specific category or label. The model analyzes the image as a whole and determines which predefined class it belongs to. For example, in this case, the model would look at the features of each image and decide whether it shows a polar bear or a brown bear. The Microsoft Learn materials define classification as “assigning an image to a specific category.”

Object Detection → Determine the location of a bear in a photoObject detection identifies where objects appear within an image by drawing bounding boxes around them. This type of model not only classifies what object is present but also provides its location. Microsoft Learn explains that object detection “detects and locates individual objects within an image.” For instance, the model can detect a bear in a forest scene and highlight its position.

Semantic Segmentation → Determine which pixels in an image are part of a bearSemantic segmentation is the most detailed form of image analysis. It classifies each pixel in an image according to the object it belongs to. In this scenario, the model identifies every pixel corresponding to the bear’s body. The AI-900 content defines this as “classifying every pixel in an image into a category.”

To summarize:

Image classification → Categorizes entire images.

Object detection → Locates and labels objects within images.

Semantic segmentation → Labels each pixel for precise object boundaries.

https://nanonets.com/blog/how-to-do-semantic-segmentation-using-deep-learning/

In Microsoft Azure OpenAI Service and the AI-900/AI-102 study materials, grounding data is the correct term used to describe the process of providing contextual or external information to improve the accuracy, relevance, and quality of responses generated by a generative AI model such as GPT-3.5 or GPT-4.

Grounding is a prompt engineering technique where the AI model is supplemented with relevant background data, such as company documents, knowledge bases, or user context, that helps the model generate factually correct and context-aware responses. Microsoft Learn defines grounding as a way to connect the model’s general knowledge to specific, real-world information. For example, if you ask a GPT-3.5 model about your organization’s HR policies, the base model will not know them unless that policy information is provided (grounded) in the prompt. By embedding this contextual data, the AI becomes “grounded” in the facts it needs to respond reliably.

This technique differs from other prompt engineering concepts:

A. Providing examples (few-shot prompting) shows the model sample inputs and outputs to guide formatting or style, not factual context.

B. Fine-tuning involves retraining the model with labeled data to permanently adjust its behavior — it’s not a prompt-based technique.

D. System messages define the model’s role, tone, or style (for example, “You are a helpful assistant”) but do not add factual context.

Therefore, when you provide contextual information (like product details, policy documents, or reference text) within a prompt to enhance the quality and factual reliability of the model’s responses, you are applying the grounding data technique.

To extract structured data such as transaction date, merchant name, total amount, and taxes from receipts, the best service is Azure AI Document Intelligence (formerly known as Form Recognizer). As described in the Microsoft Learn module: “Extract data from documents with Azure AI Document Intelligence”, this service applies optical character recognition (OCR) combined with machine learning models to identify and extract key-value pairs and tabular data from semi-structured documents like invoices, receipts, and forms.

The prebuilt receipt model of Document Intelligence can automatically recognize common receipt fields, including:

Merchant Name

Transaction Date

Total Amount

Taxes

Items Purchased

It outputs structured JSON that can easily be converted into spreadsheet or database entries. This capability eliminates the need for manual data entry, ensuring accuracy and efficiency in digitizing financial documents.

The other options are incorrect:

A. Face detects and verifies human faces but does not extract text or numerical data.

B. Azure AI Language analyzes text sentiment, key phrases, and entities but does not interpret scanned documents.

D. Azure AI Custom Vision is for training image classification or object detection models, not document data extraction.

Therefore, the most accurate and Microsoft-verified service for converting receipts into structured transactions in a spreadsheet is C. Azure AI Document Intelligence.

According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module “Explore computer vision in Microsoft Azure,” there are multiple types of computer vision tasks, each designed for different goals such as recognizing, categorizing, or locating objects within an image.

In this question, the application performs two distinct tasks: locating birds within an image and identifying their species. Each of these corresponds to a different type of computer vision capability.

Locate the birds → Object detection

Object detection is used when an AI system needs to identify and locate multiple objects within a single image.

It not only recognizes what the object is but also provides bounding boxes that indicate the exact position of each object.

In this scenario, locating the birds (drawing rectangles around each bird) is achieved through object detection models, such as those available in the Azure Custom Vision Object Detection domain.

Identify the species of the birds → Image classification

Image classification focuses on identifying what is in the image rather than where it is.

It assigns a single label (or multiple labels in multilabel classification) to an entire image based on its contents.

In this case, determining the species of a bird (e.g., robin, eagle, parrot) is achieved through image classification, where the model compares visual features against learned patterns from training data.

Incorrect options:

Automated captioning generates descriptive sentences about an image, not object locations or classifications.

Optical character recognition (OCR) extracts text from images, irrelevant in this case.

A: R-squared (R2), or Coefficient of determination represents the predictive power of the model as a value between -inf and 1.00. 1.00 means there is a perfect fit, and the fit can be arbitrarily poor so the scores can be negative.

C: RMS-loss or Root Mean Squared Error (RMSE) (also called Root Mean Square Deviation, RMSD), measures the difference between values predicted by a model and the values observed from the environment that is being modeled.

This question evaluates understanding of the different Azure AI Computer Vision services and their distinct functionalities, as covered in the Microsoft AI-900 study guide and Microsoft Learn modules under “Describe features of common AI workloads” and “Identify Azure services for computer vision.”

Azure AI Document Intelligence (formerly known as Form Recognizer):This service is designed to extract structured information from documents, such as forms, receipts, and invoices. It uses optical character recognition (OCR) combined with AI models to detect key-value pairs, tables, and handwritten text. This makes it ideal for automating data entry and digitizing scanned documents. Hence, it matches “Extract information from scanned forms and invoices.”

Azure AI Vision (formerly Computer Vision):This service provides image and video analysis capabilities. It can detect objects, people, text, and scenes; generate image captions; and extract descriptive tags. It also supports OCR for printed and handwritten text within images. Therefore, it matches “Analyze images and video, and extract descriptions, tags, objects, and text.”

Azure AI Custom Vision:Custom Vision allows you to train your own image classification and object detection models using your own labeled images. Unlike the general Vision service, Custom Vision lets you build domain-specific models—for example, detecting your company’s products or identifying manufacturing defects. Hence, it matches “Train custom image classification and object detection models by using your own images.”

These three services complement each other within Azure’s computer vision ecosystem, collectively supporting both general-purpose and specialized AI solutions for visual data analysis.

According to the Microsoft Azure AI Fundamentals (AI-900) curriculum and Azure OpenAI documentation, the appropriate service for detecting and managing harmful, unsafe, or inappropriate content in text, images, or other generative AI outputs is Azure AI Content Safety.

Azure AI Content Safety is designed to automatically detect potentially harmful material such as hate speech, violence, self-harm, sexual content, or profanity. It ensures that generative AI applications like chatbots, image generators, and content creation tools comply with Microsoft’s Responsible AI principles — specifically Reliability & Safety and Accountability.

This service integrates directly with the Azure OpenAI Service, meaning that when developers build AI solutions using models like GPT-4 or DALL·E, they can use Content Safety to filter and moderate both input prompts and model outputs. This protects users from unsafe or offensive content generation.

Let’s analyze why the other options are incorrect:

A. Face – The Face service detects and analyzes human faces in images or videos. It is unrelated to moderating harmful textual or generative content.

B. Video Analysis – This service analyzes video streams to detect objects, actions, or events but not inappropriate or harmful text or imagery from AI models.

C. Language – The Azure AI Language service focuses on text understanding tasks like sentiment analysis, entity recognition, and translation, not content safety filtering.

Therefore, per Microsoft Learn’s official AI-900 guidance, when identifying or filtering harmful content in a generative AI solution built with Azure OpenAI, the correct and verified service to use is Azure AI Content Safety.