Microsoft AI-900 Online Practice Questions and Exam Preparation

Microsoft AI-900 Online Questions & Answers

• Question 371:

  Which Azure Al Document Intelligence prebuilt model should you use to extract parties and jurisdictions from a legal document?

  A. contract
  B. layout
  C. general document
  D. read
  C. general document

• Question 372:

  DRAG DROP

  Match the Azure Cognitive Services service to the appropriate actions.

  To answer, drag the appropriate service from the column on the left to its action on the right. Each service may he used once, more than once, or not at all.

  NOTE: Each correct match is worth one point.

  Select and Place:

  

  

  ---

  Box 1: Speech

  Custom Speech: Code-free automated machine learning for speech recognition Speech to text is a Speech service feature that accurately transcribes spoken audio to text.

  Make spoken audio actionable

  Quickly and accurately transcribe audio to text in more than 100 languages and variants. Customize models to enhance accuracy for domain-specific terminology. Get more value from spoken audio by enabling search or analytics on transcribed text or facilitating action-all in your preferred programming language.

  Box 2: Language service

  Add intents to your LUIS app to identify groups of questions or commands that have the same intention.

  Note: Language understanding (LU) is a very centric component to enable conversational services such as bots, IoT experiences, analytics, and others. In a spoken dialog system, LU converts from the words in a sentence into a machine-readable meaning representation, typically indicating the intent of the sentence and any present entities. For example, consider a physical tness domain, with a dialog system embedded in a wearable device like a watch. This dialog system could recognize intents like StartActivity and StopActivity, and could recognize entities like ActivityType. In the user input "begin a jog", the goal of LU is to identify the intent as StartActivity, and identify the entity ActivityType= ''jog''.

  Box 3: Language service

  Intent compared to entity

  The intent represents the action the application should take for the user, based on the entire utterance. An utterance can have only one top-scoring intent, but it can have many entities.

  Create an intent when the user's intention would trigger an action in your client application, like a call to the checkweather() function from the table above. Then create entities to represent parameters required to execute the action.

  References:

  https://azure.microsoft.com/en-us/services/cognitive-services/speech-to-texthttps://azure.microsoft.com/en-us/blog/luis-ai-automated-machine-learning-for-custom-language-understanding/https://docs.microsoft.com/en-us/azure/cognitive-services/luis/concepts/intents

• Question 373:

  You are evaluating whether to use a basic workspace or an enterprise workspace in Azure Machine Learning.

  What are two tasks that require an enterprise workspace? Each correct answer presents a complete solution.

  NOTE: Each correct selection is worth one point.

  A. Use a graphical user interface (GUI) to run automated machine learning experiments.
  B. Create a compute instance to use as a workstation.
  C. Use a graphical user interface (GUI) to define and run machine learning experiments from Azure Machine Learning designer.
  D. Create a dataset from a comma-separated value (CSV) file.
  A. Use a graphical user interface (GUI) to run automated machine learning experiments.
  C. Use a graphical user interface (GUI) to define and run machine learning experiments from Azure Machine Learning designer.

  ---

  Explanation

  Note: Enterprise workspaces are no longer available as of September 2020. The basic workspace now has all the functionality of the enterprise workspace.

  References:

  https://www.azure.cn/en-us/pricing/details/machine-learning/https://docs.microsoft.com/en-us/azure/machine-learning/concept-workspace

• Question 374:

  HOTSPOT

  To complete the sentence, select the appropriate option in the answer area.

  

  

  ---

  References:

  https://www.cloudfactory.com/data-labeling-guide

• Question 375:

  A developer wants to design and evaluate complex prompt workflows for generative AI applications.

  Which Azure AI Foundry feature supports this capability?

  A. Prompt flow
  B. Resource group
  C. Storage explorer
  D. Data labeling
  A. Prompt flow

  ---

  Explanation

  Prompt flow allows developers to design, test, and evaluate prompt pipelines for generative AI solutions. It helps visualize prompt steps and evaluate outputs.

• Question 376:

  HOTSPOT

  Select the answer that correctly completes the sentence.

  

  

  ---

  Safety system. According to the Microsoft Learn documentation and the AI-900: Microsoft Azure AI Fundamentals official study guide, the safety system layer in generative AI architecture plays a crucial role in monitoring, filtering, and mitigating harmful or unsafe model outputs. This layer works alongside the model and user experience layers to ensure that generative AI systems-such as those powered by Azure OpenAI-produce responses that are safe, aligned, and responsible. The safety system layer uses various techniques including content filtering, prompt moderation, and policy enforcement to prevent outputs that could be harmful, biased, misleading, or inappropriate. It evaluates both user inputs (prompts) and model-generated outputs to identify and block unsafe or unethical content. The system might use predefined rules, classifiers, or human feedback signals to decide whether to allow, modify, or stop a response. In contrast, the other layers serve different purposes: The model layer contains the core large language or generative model (e.g., GPT or DALL-E) that processes inputs and produces outputs. The metaprompt and grounding layer ensures the model's responses are contextually relevant and factually supported, often linking to organizational data sources or system prompts. The user experience layer defines how users interact with the AI system, including the interface and conversational flow, but does not manage safety enforcement. Therefore, the layer that uses system inputs and context to mitigate harmful outputs from a generative AI model is the Safety system layer. This aligns with Microsoft's responsible AI principles-Fairness, Reliability and Safety, Privacy and Security, Inclusiveness, Transparency, and Accountability-ensuring generative AI operates ethically and safely.

• Question 377:

  Providing contextual information to improve the responses quality of a generative Al solution is an example of which prompt engineering technique?

  A. providing examples
  B. fine-tuning
  C. grounding data
  D. system messages
  C. grounding data

• Question 378:

  HOTSPOT

  Select the answer that correctly completes the sentence.

  

  

  ---

  Box 1: detection.

  Attributes are a set of features that can optionally be detected by the Face - Detect API. The following attributes can be detected:

  * Exposure. The exposure of the face in the image. This attribute returns a value between zero and one and an informal rating of underExposure, goodExposure, or overExposure.

  * Noise. The visual noise detected in the face image. This attribute returns a value between zero and one and an informal rating of low, medium, or high.

  * Occlusion. Whether there are objects blocking parts of the face. This attribute returns a Boolean value for eyeOccluded, foreheadOccluded, and mouthOccluded.

  * Etc.

  References:

  https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-face-detection

• Question 379:

  What should you do to reduce the number of false positives produced by a machine learning classification model?

  A. Include test data in the training data.
  B. Increase the number of training iterations.
  C. Modify the threshold value in favor of false positives.
  D. Modify the threshold value in favor of false negatives.
  D. Modify the threshold value in favor of false negatives.

• Question 380:

  You need to create a customer support solution to help customers access information. The solution must support email, phone, and live chat channels.

  Which type of Al solution should you use?

  A. natural language processing (NLP)
  B. computer vision
  C. machine learning
  D. chatbot
  D. chatbot

  ---

  Explanation

  AI chatbots use natural language processing (NLP) to help users to interact with web services or apps through text, graphics, or speech. Chatbots can understand natural human language, emulate human conversation, and run simple, automated tasks. In addition, AI chatbots use predictive intelligence and analytics to learn a user's preferences and use this knowledge to provide recommendations and anticipate needs.

  AI chatbots are used in a variety of channels, such as messaging apps, mobile apps, websites, phone lines, and voice-enabled apps. They can be developed to handle just a few simple commands or to serve as complex digital assistants and interactive agents. An AI chatbot can be a part of a larger application or be completely stand-alone.

  References:

  https://powervirtualagents.microsoft.com/en-us/ai-chatbot/