AI 901

Question #1 (Topic 1) You are using the Azure Speech SDK to develop a Python application that supports real-time spoken conversations. Which Azure Speech class should you use to configure the connection to the Azure Speech service?. A. AudioOutputConfig. B. SpeechSynthesizer. C. AudioConfig. D. SpeechConfig.

Question #2 (Topic: 1) HOTSPOT Select the answer that correctly completes the sentence. When using the OpenAI responses API and a vision-enable model, you can include an image in a request by providing the image as: a base64-enconded image data. a CSV file attachment. an MP4 video stream. a shared access signature (SAS) token.

Question #3 (Topic: 1) You need to create an AI agent in Microsoft Foundry that follows a specific role and behavior when responding to users. What should you configure?. A. system instructions. B. temperature. C. tokens per minute (TPM). D. max completion tokens.

Question #4 (Topic 1) HOTSPOT For each of the following statements, please check if Yes if the statement is true. Otherwise, select No and leave blank NOTE: Each correct selection is worth one point. System prompts can be used to authorize users. A system prompt is used to reduce tokens per minute (TPM). A system prompt guides the behaviors of a generative AI model.

Question #5 (Topic 1) You are developing a web app that processes invoices to calculate expenses. You need to extract structured fields, including nested values, from the invoices by using a defined schema. What should you use?. A. an optical character recognition (OCR)-only document processing pipeline. B. a transcription workflow in Azure Speech in Foundry Tools. C. an analyzer in Azure Content Understanding in Foundry Tools. D. an Azure AI Search service.

Question #6 (Topic: 1) HOTSPOT For each of the following statements, select Yes and check the box if the statement is true. Otherwise, if NO leave blank NOTE: Each correct selection is worth one point. Voice Live returns only transcribed text. Voice Live requires you to separately implement speech to text and text to speech services. Voice Live combines speech to text, reasoning and text to speech into a single conversational experience.

Question #7 (Topic: 1) You are developing a voice application that listens for spoken commands and converts them into text by using Azure Speech in Foundry Tools. How should you complete the Python code? To answer, select the appropriate option in the answer area. NOTE: Each correct selection is worth one point. Code Area: import azure.cognitiveservices.speech as speechsdk ... speech_config = speechsdk.SpeechConfig(subscription=key, region=region) recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config) [Select an option]. recognizer.recognize_once(). recognizer.speak_text_async("Ready"). recognizer.start_continuous_recognition(). recognizer.start_keyword_recognition().

Question #8 (Topic: 1) What are two purposes of instructions when prompting a generative AI model? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point. A. defines the agent’s role and behavior. B. selects which model to use. C. defines the Azure region where inference occurs. D. defines the tokens per minute (TPM) allocation for the model. E. defines constraints on the model’s responses.

Question #9 (Topic 1) HOTSPOT You are developing an application that converts text into spoken audio and saves the synthesized audio to a file by using Azure Speech in Foundry Tools. How should you complete the Python code? To answer, select the appropriate option in the answer area. NOTE: Each correct selection is worth one point. import azure.cognitiveservices.speech as speechsdk speech_config = speechsdk.SpeechConfig(subscription=key, region=region) audio_config = speechsdk.audio. [Select an option] synthesizer = speechsdk.SpeechSynthesizer( speech_config=speech_config, audio_config=audio_config Options available: AudioOutputConfig(filename="output.wav"). AudioOutputConfig(stream). AudioStreamFormat(wave_stream_format=AudioStreamWaveFormat.PCM).

Question #10 (Topic :1) HOTSPOT Select the answer that correctly completes the sentence. To define an agent's role and behaviors, you must configure a ________ for the agent. deployment slot. embedding index. fine-tuning job. system prompt.

Question #: 11 [Topic : 1] HOTSPOT You are developing an application that analyze invoices by using Azure Content Understanding in Foundry Tools. You need to ensure that the application retrieves the analysis results after processing completes. How should you complete the Python code? To answer, select the appropriate option in the answer area. NOTE: Each correct selection is worth one point. Answer Area: poller = client.begin_analyze( analyzer_id="invoice", input_url=url ) result = poller.[Select an option]. get_results. result. status. wait.

Question #: 12 Topic : 1 Check for the blank spaces You have a Microsoft Foundry project named project1 that contains an Azure OpenAI resource named Resource1. To Resource1, you deploy a gpt-4.1-mini model by using a model deployment named my-mini-gpt. You need to connect to my-mini-gpt from an application. How should you complete the Python code? To answer, check the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. NOTE: Each correct selection is worth one point. CODE SECTION: client = OpenAI(api_key="...", base_url="https://[ ____________ ].openai.azure.com/openai/v1/") response = client.responses.create( model="[____________ ]", ..) Values. gpt-4.1-mini. my-mini-gpt. project1. resource1.

Question 90 | Topic 1 You are building an AI solution that processes customer information. Which task is an example of the Microsoft responsible AI principle of privacy and security?. A. Encrypt stored customer data and restrict system access by using role-based controls. B. Provide explanations about how the system generates predictions. C. Test the system under unexpected conditions to prevent harmful failures. D. Evaluate model outputs across demographic groups to reduce bias.

Question 91 | Topic 1 You deploy an AI system to assist with hiring decisions. Company policy requires that human reviewers oversee AI-generated recommendations and remain responsible for final hiring decisions. Which Microsoft responsible AI principle is this an example of?. A. reliability and safety. B. fairness. C. transparency. D. accountability.

Question 92 | Topic 1 | HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Statement 1 All AI models can analyze and generate images. Yes. No.

Question 92 | Topic 1 | HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Statement 2 A vision-enabled generative AI model can extract text from images. Yes. No.

Question 92 | Topic 1 | HOTSPOT Statement 3 A multimodal model can process prompts that include both text and images. Yes. No.

Question 93 | Topic 1 You need to build an AI solution that responds to user queries with detailed written explanations. Which type of AI model should you use?. A. an image generation model. B. a speech recognition model. C. a text generation model. D. an embedding model.

Question 94 | Topic 1 | Multiple Answers What are two types of generative AI models? Each correct answer presents a complete solution. NOTE: Each correct answer is worth one point. A. computer vision. B. GPT. C. DALL-E. D. transformer. E. natural language processing.

Question 95 | Topic 1 You are building a chatbot that will use natural language processing (NLP) to perform the following actions based on the text input of a user: Accept customer orders. Retrieve support documents. Retrieve order status updates. Which type of NLP should you use?. A. sentiment analysis. B. named entity recognition. C. translation. D. language understanding.

Question 96 | Topic 1 You have the following REST API request. body = { "prompt": "A polar bear on the beach holding an icecream", "size": "1024x1024", "n": 1, "style": "vivid" } Which Azure OpenAI model should you use to process the request?. A. DALL-E. B. Codex. C. GPT-4.1. D. Whisper.

Question 97 | Topic 1 | HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Statement 1 You can deploy a supported base model directly from the model catalog. Yes. No.

Question 97 | Topic 1 | HOTSPOT Statement 2 The playground is used to create the model deployment before the model can be tested. Yes. No.

Question 97 | Topic 1 | HOTSPOT Statement 3 After deploying a model, you can use the playground in the Microsoft Foundry portal to send prompts and review responses. Yes. No.

Question 98 - Topic 1 You have a Microsoft Foundry project that contains a vision-enabled chat model deployment. You are developing a Python application that uses the responses API. The application sends a request that includes a user prompt and a local JPEG image. You need to include the local image in the request. Which value should you use for the image input?. A. data:image/jpeg;base64,. B. C:\images\photo.jpg. C. file:///C:/images/photo.jpg. D. https://.blob.core.windows.net//.jpg.

Question 99 | Topic 1 | Select the answer that correctly completes the sentence. _____ is used to extract dates, quantities, and locations from text. Options: A. Key phrase extraction. B. Language detection. C. Named Entity Recognition (NER). D. Sentiment Analysis.

Question 100 | Topic 1 You have a Microsoft Foundry project that contains a deployed generative AI model. You need to develop an application by using the Microsoft Foundry SDK to send chat prompts to the deployed model. Which information must the application include?. A. Model training dataset, exported playground session history, and Foundry project display name. B. Exported playground session history, endpoint URL and task type. C. Credentials, endpoint URL, and model deployment name. D. Foundry project display name, model training dataset, and task type.

Question 101 | Topic 1 Which action can be performed by using the Azure Vision in Foundry Tools service?. A. creating thumbnails for training videos. B. extracting key phrases from documents. C. identifying breeds of animals in live video streams. D. extracting data from handwritten letters.

Question 102 | Topic 1 Which natural language processing feature can be used to identify the main talking points in customer feedback surveys?. A. translation. B. language detection. C. entity recognition. D. key phrase extraction.

Question 103 | Topic 1 Stating the source of the data used to train a model is an example of which responsible AI principle?. A. privacy and security. B. reliability and safety. C. fairness. D. transparency.

Question 104 | Topic 1 You plan to create an AI application that will use Azure OpenAI in Foundry Models. The solution requires that a specific amount of throughput be allocated. Which type of deployment should you use?. A. provisioned. B. standard. C. global batch. D. data zone standard.

Question 105 | Topic 1 You are building an AI-based loan approval app. You need to ensure that the app documents why a loan is approved or rejected and makes the report available to the applicant. This is an example of which Microsoft responsible AI principle?. A. transparency. B. accountability. C. fairness. D. inclusiveness.

Question 106 | Topic 1 Verifying that machine learning models do NOT show racial or gender bias is an example of which Microsoft responsible AI principle?. A. safety. B. reliability. C. fairness. D. privacy and security.

Question #: 107 Topic #: 1 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Speech synthesis converts spoken audio into written text. Yes. No.

Question #: 107 Topic #: 1 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Speech recognition can be detect and transcribe spoken input. Yes. No.

Question #: 107 Topic #: 1 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Text to speech in Azure speech in Fountry Tools can translate text input into audible speech in a different language. Yes. No.

Question #: 108 Topic #: 1 HOTSPOT Select the answer that correctly completes the sentence. fairness. reliability and safety. accountability. inclusiveness.

Question #: 109 Topic #: 1 DRAG DROP Match the principles of responsible AI to appropriate requirements. To answer, drag the appropriate principles from the column on the left to its requirement on the right. Each principle may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content. NOTE: Each correct selection is worth one point. Fairness. Privacy and security. Reliability and safety. transparency.

Question #: 110 Topic #: 1. forecasting. computer vision. knowledge mining.

Question 60 You are developing an application that records a user's voice and sends the recorded audio to a deployed multimodal model in Microsoft Foundry. You need to send the user's request to the model. What should you include in the request?. A. an image of the audio frames. B. a text transcript of the voice. C. an audio input prompt. D. a text embedding vector.

Question 81 You need to deploy a generative AI model to a Microsoft Foundry project. Which factor should you use to identify which type of model can be deployed to the project?. A. the token size. B. Azure region availability. C. the authentication method. D. REST API support.

Question 82 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Question 82.1 Image analysis capabilities in Microsoft Foundry Tools can perform optical character recognition (OCR). Yes. No.

Question 82 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Question 82.2 Image analysis capabilities in Microsoft Foundry Tools can generate captions and descriptive tags for images. Yes. No.

Question 82 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 82.3 Image analysis capabilities in Microsoft Foundry Tools are designed primarily to create new images from text prompts. Yes. No.

Question 84 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Question 84.1 Using Azure Speech in Foundry Tools for batch transcription requires live audio input from a microphone. Yes. No.

Question 84 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 84.2 Azure Speech in Foundry Tools can analyze video frames to detect and label objects while transcribing audio. Yes. No.

Question 84 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 84.3 Speech translation in Azure Speech in Foundry Tools only supports translating speech into spoken output in another language. Yes. No.

Question 85 HOTSPOT Select the answer that correctly completes the sentence. After a generative AI model is deployed, applications send requests to the model by calling the _____ of the model. A. API endpoint. B. embedding vector. C. training dataset. D. URL parameter.

Question 86 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Question 86.1 Generative AI models predict the next token in a sequence based on patterns learned during training. Yes. No.

Question 86 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 86.2 A system prompt can be used to influence the behavior and tone of the responses generated by a generative AI model. Yes. No.

Question 86 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 86.3 Increasing the Temperature parameter makes the responses generated by generative AI models more deterministic and consistent. Yes. No.

Question 88 Your company provides users with clear information about an AI system's purpose, functionality, and limitations. Which Microsoft responsible AI principle is this an example of?. A. transparency. B. accountability. C. fairness. D. reliability and safety.

Question 89 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 89.1 Transparency focuses on increasing system performance and throughput. Yes. No.

Question 89 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 89.2 Transparency is supported when users are informed about an AI system's purpose and limitations. Yes. No.

Question 89 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 89.3 Providing meaningful explanations of how an AI system generates its results supports transparency. Yes. No.

Question 111 Which type of Azure AI workload should you use to create illustrations based on the text of an article?. A. generative AI. B. Azure Document Intelligence in Foundry Tools. C. computer vision. D. natural language processing.

Question 112 Capturing text from images is an example of which type of AI capability?. A. object detection. B. text analysis. C. optical character recognition (OCR). D. image description.

Question 113 HOTSPOT Select the answer that correctly completes the sentence. Counting the number of animals in an area based on a video feed is an example of _____. A. forecasting. B. computer vision. C. knowledge mining.

Question 114 HOTSPOT Select the answer that correctly completes the sentence. A computer vision model _____. A. analyzes images to detect objects. B. creates new visual content based on text prompts. C. organizes structured numerical data into predictive categories. D. uses pattern matching to retrieve similar images from a fixed database.

Question 115 You have the process shown in the exhibit. The diagram shows a user asking: "How do I programmatically update my Knowledge Base?" The system receives the request and returns an interactive response: "You can use our REST APIs to manage your Knowledge Base. See here for details: https://aka.ms/kb-info" Which type of AI solution is shown in the diagram?. A. a sentiment analysis solution. B. a computer vision application. C. an agent. D. a machine learning model.

Question 116 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 116.1 Whisper models in Azure OpenAI are used to convert speech to text. Yes. No.

Question 116 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 116.2 Embedding models in Azure OpenAI are used to convert text into numeric vectors. Yes. No.

Question 116 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 116.3 GPT-4.1 models in Azure OpenAI are used to generate images based on natural language prompts. Yes. No.

Question 117 In which two scenarios can you use speech recognition? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point. A. creating a transcript of a telephone call or meeting. B. an in-car system that reads text messages aloud. C. creating an automated public address system for a train station. D. providing closed captions for recorded or live videos.

Question 118 You have 100 instructional videos that do NOT contain any audio. Each instructional video has a script. You need to generate a narration audio file for each video based on the script. Which type of workload should you use?. A. translation. B. speech recognition. C. language modeling. D. speech synthesis.

Question 119 What is an example of the Microsoft responsible AI principle of transparency?. A. ensuring that developers are accountable for the solutions they create. B. ensuring that opportunities are allocated equally to all applicants. C. helping users understand the decisions made by an AI system. D. ensuring that the privileged data of users is stored in a secure manner.

Question 120 HOTSPOT Select the answer that correctly completes the sentence. _____ can be used to extract text from images. A. Computer vision. B. Generative AI. C. Natural language processing.

Question 121 You have an AI-based loan approval system. During testing, you discover that the system has a gender bias. Which responsible AI principle does this violate?. A. reliability and safety. B. transparency. C. accountability. D. fairness.

Question 122 DRAG DROP Match the description to the corresponding Microsoft Foundry tools. Extracts entities from the output. Generates spoken output. Transcribes spoken input.

Question 123 You plan to deploy a generative AI model to a Microsoft Foundry project in the East US Azure region. What should you check first?. A. Model availability. B. the token limit. C. REST API support. D. the authentication method.

Question 124 HOTSPOT Select the answer that correctly completes the sentence. _____ converts spoken audio into text. A. Azure Language in Foundry Tools. B. Azure Speech in Foundry Tools. C. Azure Vision in Foundry Tools. D. Azure OpenAI in Foundry Models.

Question 125 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 125.1 All AI models can analyze and generate images. Yes. No.

Question 125 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 125.2 A multimodal generative AI model can interpret image input in a prompt. Yes. No.

Question 125 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 125.3 A multimodal model can process prompts that include both text and images. Yes. No.

Question 126 You are designing an AI system that empowers everyone, including people who have hearing, visual, and other impairments. This is an example of which Microsoft guiding principle for responsible AI?. A. accountability. B. reliability and safety. C. fairness. D. inclusiveness.

Question 127 HOTSPOT Select the answer that correctly completes the sentence. The interactive answering of questions entered by a user as part of an application is an example of _____. A. computer vision. B. natural language processing. C. forecasting.

Question 128 Which two scenarios are examples of a natural language processing workload? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point. A. monitoring the temperature of machinery to turn on a fan when the temperature reaches a specific threshold. B. assembly line machinery that autonomously inserts headlamps into cars. C. a smart device in the home that responds to questions such as, "What will the weather be like today?". D. an agent on a website that uses a knowledge base to interactively respond to users' questions.

Question 129 DRAG DROP Match the principles of responsible AI to the appropriate descriptions. Principles. Fairness. Inclusiveness. Privacy and security. Reliability and safety.

Question 130 You are building an application that uses Azure Speech in Foundry Tools. You need to initialize the Speech SDK for Python by creating a SpeechConfig object. Which values should you specify?. A. the storage account key and connection string. B. the Foundry resource key and endpoint. C. the model deployment name and model endpoint. D. the Foundry project name and project endpoint.

Question 131 HOTSPOT Select the answer that correctly completes the sentence. When using Azure Language in Foundry Tools, use _____ to identify people, places, and events. Options: conversation Personally Identifiable Information (PII). language detection. named entity recognition (NER). Text analytics for health.

Question 132 HOTSPOT Select the answer that correctly completes the sentence. When using Azure Language in Foundry Tools, use ___________ to identify people, places, and events. The visible dropdown options in the screenshot are: analyzes images to detect objects. creates new visual content based on text prompts. organizes structured numerical data into predictive categories. uses pattern matching to retrieve similar images from a fixed database. Named Entity Recognition (NER).

Question 133 You are developing an application that analyzes voicemail recordings by using Azure Content Understanding in Foundry Tools. You need to transcribe the recordings and extract structured information from the audio. Which type of analyzer should you use?. A. image analyzer. B. document analyzer. C. audio analyzer. D. video analyzer.

Question 134 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Question 134.1 Restricting users to authorized data reduces the risk of sensitive data exposure when they use AI systems. Yes. No.

Topic 1 | Question 134 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 134.2 Sharing personal user data improves collaboration and supports responsible AI practices. Yes. No.

Question 134 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 134.2 Sharing personal user data improves collaboration and supports responsible AI practices. Yes. No.

Question 135 You have a website that includes customer reviews. You need to store the reviews in English and present the reviews to users in their respective language based on each user's geographical location. Which type of natural language processing workload should you use?. A. key phrase extraction. B. translation. C. speech recognition. D. language modeling.

Question 136 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Question 136.1 You can use the Azure Speech in Foundry Tools service to transcribe a call to text. Yes. No.

Question 136 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 136.2 You can use the Azure Language in Foundry Tools service to extract key entities from a call transcript. Yes. No.

Question 136 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 136.3 You can use the Azure Speech in Foundry Tools service to translate the audio of a call to a different language. Yes. No.

Question 137 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 137.1 Saving an agent in the Microsoft Foundry portal creates a version that can be tested in the Agents playground. Yes. No.

Question 137 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 137.2 Publishing an agent is required before you can test the agent in the Agents playground. Yes. No.

Question 137 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 137.3 Publishing an agent can make the agent available through a stable endpoint or supported channel. Yes. No.

Question 138 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 138.1 Designing an AI system for a typical user profile is sufficient to support inclusiveness. Yes. No.

Question 138 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 138.2 A high number of active users means an AI system provides an inclusive experience. Yes. No.

Question 138 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 138.3 Providing accessible interfaces and language options helps support inclusiveness in an AI system. Yes. No.

Question 139 HOTSPOT Select the answer that correctly completes the sentence. _____ is an example of speech recognition. A. A voice-activated security key system. B. Creating an audio commentary for a video recording. C. Creating captions for a video recording. D. Identifying key phrases in a video transcript.

Question 141 HOTSPOT Select the answer that correctly completes the sentence. Asking a chatbot whether it will rain and being provided with a weather report is an example of _____. A. computer vision. B. natural language processing. C. prediction and forecasting.

Question 142 HOTSPOT Select the answer that correctly completes the sentence. Natural language processing can be used to _____. A. classify email messages as work-related or personal. B. predict the number of future car rentals. C. predict which website visitors will make a transaction. D. stop a process in a factory when extremely high temperatures are registered.

Question 143 DRAG DROP You are designing a system that will generate insurance quotes automatically. Match the Microsoft responsible AI principles to the appropriate requirements. Each principle may be used once, more than once, or not at all. Principles. Accountability. Fairness. Inclusiveness. Privacy and security. Reliability and safety. Transparency.

Question 144 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 144.1 A multimodal chat completion model can accept audio input in a user message. Yes. No.

Question 144 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 144.2 The embeddings endpoint is used to send spoken prompts to a multimodal chat completion model. Yes. No.

Question 144 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 144.3 In a REST chat completions request, audio file content can be sent as an input_audio content item. Yes. No.

Question 145 HOTSPOT Select the answer that correctly completes the sentence. _____ are goals of the Reliability & Safety principle in the Microsoft Responsible AI Standard Playbook. Options. A. Human oversight and control. B. Data governance and management. C. Ongoing monitoring, feedback, and evaluation. D. The minimization of stereotyping, demeaning, and erasing outputs.

Question 146 Which statement is an example of a Microsoft responsible AI principle?. A. AI systems must be understandable. B. AI systems must keep personal details public. C. AI systems must use only publicly available data. D. AI systems must protect the interests of the company.

Question 147 Which Azure OpenAI model should you use to summarize the text from a document?. A. GPT-5. B. Whisper. C. Codex. D. DALL-E.

Question 148 Which feature of the Azure Language in Foundry Tools service should you use to automate the masking of names and phone numbers in text data?. A. Personally Identifiable Information (PII) detection. B. custom text classification. C. entity linking. D. custom named entity recognition (NER).

Question 149 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 149.1 The Azure Language in Foundry Tools service can identify in which language text is written. Yes. No.

Question 149.2 The Azure Language in Foundry Tools service can detect handwritten signatures in a document. Yes. No.

Question 149.3 The Azure Language in Foundry Tools service can identify companies and organizations mentioned in a document. Yes. No.

Question 150 You use natural language processing to process text from a Microsoft news story. You receive the output shown in the following table. Input For weeks now, students and teachers have been settling into the uncharted routine of distance learning. Today I want to thank all of the educators who are connecting classrooms and classmates together in the sudden shift to remote learning. This change requires everyone working together and is unlike anything we've seen in the modern history of education. We've seen countries, school districts and universities move rapidly into remote learning environments with Microsoft Teams being used in 175 countries by 183,000 institutions. Output now [DateTime] students [PersonType] teachers [PersonType] distance learning [Skill] Today [DateTime-Date] educators [PersonType] classrooms [Location] classmates [PersonType] remote learning [Skill] history [Skill] education [Skill] remote learning [Skill] Microsoft [Organization] 175 [Quantity-Number] 183,000 [Quantity-Number] Which type of natural language processing was performed?. A. entity recognition. B. sentiment analysis. C. translation. D. key phrase extraction.

Question 151 HOTSPOT Select the answer that correctly completes the sentence. _____ automatically identifies and tags elements within images for better organization and searchability. Options: Content safety. Image analysis. Optical character recognition (OCR). A small language model (SLM).

Question 152 Your company wants to build a recycling machine for bottles. The recycling machine must use cameras to automatically identify bottles of the correct shape and reject all other items. Which type of AI workload should the company use?. A. knowledge mining. B. computer vision. C. natural language processing. D. generative AI.

Question 153 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 153.1 Analyzing customer sentiment from product reviews is an example of a natural language processing workload. Yes. No.

Question 153 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 153.2 Identifying objects in images uploaded by users is a computer vision workload. Yes. No.

Question 153 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 153.3 Predicting future sales figures from old sales data is an example of generative AI. Yes. No.

Question 154 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 154.1 Human-in-the-loop practices provide accountability for AI-generated decisions. Yes. No.

Question 154 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Question 154.2 Deploying an AI system to a production environment eliminates the need for ongoing monitoring. Yes. No.

Question 154 HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No.} Question 154.3 Publishing the names of the people who built an AI system is sufficient to provide accountability. Yes. No.

Question 155 Your company is exploring the use of voice recognition technologies in its smart home devices. The company wants to identify any barriers that might unintentionally leave out specific user groups. This is an example of which Microsoft guiding principle for responsible AI?. A. inclusiveness. B. privacy and security. C. accountability. D. fairness.

Question 156 You are building an AI system. Which task should you include to help the service meet the Microsoft transparency principle for responsible AI?. A. Ensure that all visuals have an associated text that can be read by a screen reader. B. Enable autoscaling to ensure that a service scales based on demand. C. Ensure that a training dataset is representative of the population. D. Provide documentation to help developers debug code.

Question 157 HOTSPOT Select the answer that correctly completes the sentence. rrectly handling unusual or missing values is an example of an application following the _____ principle for responsible AI. Options: inclusiveness. privacy and security. reliability and safety. transparency.

Question 158 You are developing a system to predict the prices of insurance for drivers in the United Kingdom. You need to minimize unintended bias in the system. What should you do?. A. Create a training dataset that uses data from global insurers. B. Take a training sample that is representative of the population in the United Kingdom. C. Remove information about protected characteristics from the data before sampling. D. Take a completely random training sample.