Microsoft Azure AI Fundamentals (Updated Version) Version: Demo [ Total Questions: 10] Web: www.certsout.com Email: support@certsout.com Microsoft AI-901 IMPORTANT NOTICE Feedback We have developed quality product and state-of-art service to ensure our customers interest. If you have any suggestions, please feel free to contact us at feedback@certsout.com Support If you have any questions about our product, please provide the following items: exam code screenshot of the question login id/email please contact us at and our technical experts will provide support within 24 hours. support@certsout.com Copyright The product of each order has its own encryption code, so you should use it independently. Any unauthorized changes will inflict legal punishment. We reserve the right of final explanation for this statement. Microsoft - AI-901 Certs Exam 1 of 10 Pass with Valid Exam Questions Pool Category Breakdown Category Number of Questions Implement generative AI apps and agents by using Foundry 5 Implement AI solutions for information extraction by using Foundry 2 Implement AI solutions for text and speech by using Foundry 1 Describe principles of responsible AI 1 Identify AI model components and configurations 1 TOTAL 10 Question #:1 - [Implement generative AI apps and agents by using Foundry] 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: Microsoft - AI-901 Certs Exam 2 of 10 Pass with Valid Exam Questions Pool Explanation The completed code is: poller = client.begin_analyze( analyzer_id="invoice", input_url=url ) result = poller.result() Azure Content Understanding analysis uses a long-running operation pattern. The Python SDK returns a poller from begin_analyze(), and Microsoft documentation states that the SDK poller handles polling automatically when you call .result() Therefore, to retrieve the analysis results after processing completes, the correct option is: result The other options are incorrect because status checks operation state, wait waits without returning the final analysis object, and get_results is not the method shown for retrieving the begin_analyze() result in this code pattern. Question #:2 - [Implement AI solutions for information extraction by using Foundry] You are developing an application that extracts structured information from different types of content by using Azure Content Understanding in Foundry Tools. You need to extract scanned invoices in the PDF format and voicemail recordings in the WAV format. Which type of analyzer should you use for each content type? To answer, drag the appropriate analyzer types to the correct content types. Each analyzer type 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. Microsoft - AI-901 Certs Exam 3 of 10 Pass with Valid Exam Questions Pool A. Answer: Explanation Azure Content Understanding analyzers define the type of content to process, such as documents, images, , and what to extract, such as text, layout, fields, transcripts, and structured JSON output. audio, or video Microsoft lists base analyzer types such as prebuilt-document, prebuilt-audio, prebuilt-video, and prebuilt- image. For , the correct choice is , because invoices are scanned invoices in PDF format document analyzer document/form content. Microsoft’s Content Understanding quickstart specifically uses the prebuilt-invoice analyzer to extract structured data from an invoice PDF. For , the correct choice is , because voicemail is voicemail recordings in WAV format audio analyzer audio content. Content Understanding supports structured data extraction from audio files, and the analyzer reference identifies prebuilt-audio as the base analyzer for audio content. Question #:3 - [Implement generative AI apps and agents by using Foundry] You are developing an application that processes voicemail recordings by using Azure Content Understanding in Foundry Tools. Which feature does Azure Content Understanding use to convert audio to text? Microsoft - AI-901 Certs Exam 4 of 10 Pass with Valid Exam Questions Pool A. B. C. D. A. B. C. D. Voice Live key phrase extraction transcription optical character recognition (OCR) Answer: C Explanation Azure Content Understanding uses to convert audio content, such as voicemail recordings, into transcription text. Microsoft’s Azure Content Understanding audio documentation states that transcription converts conversational audio into searchable and analyzable text-based transcripts. Option is not the feature used by Content Understanding to convert voicemail recordings into A. Voice Live text. Option identifies important phrases after text is available; it is not the audio-to-text B. key phrase extraction conversion step. Option is for extracting text from images or documents, not audio. D. optical character recognition (OCR) Therefore, the correct answer is C. transcription Question #:4 - [Implement generative AI apps and agents by using Foundry] You are developing an application that extracts fields from PDFs by using Azure Content Understanding in Foundry Tools. You need to use the Python SDK to submit a PDF for analysis and retrieve the extraction results. What should you do? Call begin_analyze(), and then call poller.result() to retrieve the results. Submit the PDF to an analyzer and read the results from the request headers. Use optical character recognition (OCR) to extract text from the PDF and map the fields in the code. Call analyze() to return the extracted fields synchronously in the same request. Answer: A Explanation Microsoft - AI-901 Certs Exam 5 of 10 Pass with Valid Exam Questions Pool A. B. C. D. Azure Content Understanding analysis operations are long-running operations in the Python SDK. Microsoft’ s Python SDK documentation states that analysis operations return a poller, and the SDK provides LROPoller types that handle polling automatically when you call .result() Therefore, the correct workflow is to submit the PDF by calling , receive a poller, and then begin_analyze() call: result = poller.result() Option is incorrect because extraction results are not read from request headers. B Option is incorrect because the requirement is to use Azure Content Understanding extraction, not build a C manual OCR-only mapping pipeline. Option is incorrect because the SDK analysis pattern is asynchronous/long-running, not a simple D synchronous analyze() call that returns all extracted fields in the same request. Question #:5 - [Implement generative AI apps and agents by using Foundry] You have a Microsoft Foundry project that contains a vision-enabled model deployment. You need to develop an application that sends a message containing text and an image URL. The solution must ensure the quickest response time. Which message structure should you include in the request? a user message that includes only a text item and sends an image item in a separate request a system message that includes both a text item and an image item in the content array a system message that includes only a text item and sends an image item in a separate request a user message that includes both a text item and an image item in the content array Answer: D Explanation For a vision-enabled model, Microsoft documentation shows that multimodal prompts can include both text and content in the same user message content array. Azure OpenAI vision models accept multimodal image image-and-text input and return natural language responses. The correct request structure is a with a content array containing both items, for example: user message { "role": "user", "content": [ Microsoft - AI-901 Certs Exam 6 of 10 Pass with Valid Exam Questions Pool {"type": "input_text", "text": "What is in this image?"}, {"type": "input_image", "image_url": image_url} ] } This avoids sending separate requests and is therefore the best choice for quickest response time. A and C are incorrect because they send the text and image separately. B is incorrect because the image/question should be sent as a user message, while system messages are used for instructions and behavior. Question #:6 - [Implement AI solutions for text and speech by using Foundry] For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Answer: Explanation Microsoft - AI-901 Certs Exam 7 of 10 Pass with Valid Exam Questions Pool A. B. C. Statement 1: = Voice Live returns only transcribed text. No Voice Live is not limited to transcription. Microsoft documentation states that the Voice Live API supports real-time bidirectional voice applications, including speech recognition, text-to-speech synthesis, avatar streaming, animation data, and audio processing. Statement 2: Voice Live requires you to separately implement speech to text and text to speech services. = No Voice Live provides a single real-time voice API experience rather than requiring separate STT and TTS implementations for the conversational loop. Microsoft describes live AI voice conversations as combining speech capabilities for real-time interaction, and the Voice Live API includes speech recognition and text-to- speech synthesis features. Statement 3: Voice Live combines speech to text, reasoning, and text to speech into a single = conversational experience. Yes This is correct. Microsoft’s guidance explains that Azure OpenAI audio/realtime capabilities are for scenarios that combine audio with language understanding, reasoning, or generation in a single model call, and Voice Live supports real-time voice-enabled applications over WebSocket connections. Question #:7 - [Implement generative AI apps and agents by using Foundry] You have a Microsoft Foundry project that contains an agent named Agent1. You need to ensure that Agent1 always calls an Azure function when the agent responds to user input. To what should you set tool_choice for Agent1? auto none required Answer: C Explanation Microsoft - AI-901 Certs Exam 8 of 10 Pass with Valid Exam Questions Pool Microsoft’s Foundry Agent Service documentation states that tool_choice provides deterministic control over tool calling: auto means the model decides whether to call tools. required means the model must call one or more tools none means the model does call tools. not Therefore: A. auto = Incorrect, because the model may or may not call the Azure function. B. none = Incorrect, because this prevents tool/function calls. C. required = Correct, because it forces the agent to call a tool. The Azure OpenAI function-calling documentation also confirms that tool_choice="auto" lets the model decide whether to call a function, while tool_choice="none" forces a user-facing response without a tool call. Question #:8 - [Describe principles of responsible AI] Select the answer that correctly completes the sentence. Answer: Explanation Microsoft - AI-901 Certs Exam 9 of 10 Pass with Valid Exam Questions Pool A. B. C. D. The Microsoft responsible AI principle of transparency requires that AI systems be explainable to users Transparency means users should understand when they are interacting with AI, what the system can and cannot do, and how outputs or predictions are generated at an appropriate level. The other options map to different responsible AI principles: protect sensitive user data = Privacy and security reduce bias in decisions = Fairness require human oversight = Accountability Question #:9 - [Identify AI model components and configurations] You need to compare the costs of large language models (LLMs) for a generative AI solution. What should you use in the Microsoft Foundry portal? Evaluator catalog Model leaderboard Compliance Tools Answer: B Explanation To compare the costs of large language models in Microsoft Foundry portal, use the Model leaderboard Microsoft documentation states that the helps compare models across model leaderboard quality, safety, . It also supports trade-off charts and side-by-side model comparison for estimated cost, and throughput features, performance, and estimated cost. Why the other options are incorrect: Microsoft - AI-901 Certs Exam 10 of 10 Pass with Valid Exam Questions Pool A. B. C. D. A. Evaluator catalog is for selecting evaluators to measure model or application outputs, not comparing LLM costs. C. Compliance relates to governance and compliance, not model cost comparison. D. Tools provides Foundry tools, not benchmarked cost comparison across models. Question #:10 - [Implement AI solutions for information extraction by using Foundry] You have an Azure subscription. You need to use Azure Content Understanding in Foundry Tools to extract structured data from invoices. What should you provision? an Azure OpenAI resource a Microsoft Foundry resource A Microsoft Foundry project an Azure AI Search service Answer: B Explanation To use Azure Content Understanding in Foundry Tools, Microsoft lists a as a Microsoft Foundry resource prerequisite. The documentation states that you need a Microsoft Foundry resource created in a supported region, and that the portal lists this resource under Foundry > Foundry The invoice scenario is also directly aligned with Content Understanding’s intelligent document processing use case: Microsoft states that Content Understanding converts unstructured documents into structured data and gives invoice processing as an example. Therefore, to extract structured data from invoices by using Azure Content Understanding in Foundry Tools, you should provision a Microsoft Foundry resource About certsout.com certsout.com was founded in 2007. We provide latest & high quality IT / Business Certification Training Exam Questions, Study Guides, Practice Tests. We help you pass any IT / Business Certification Exams with 100% Pass Guaranteed or Full Refund. Especially Cisco, CompTIA, Citrix, EMC, HP, Oracle, VMware, Juniper, Check Point, LPI, Nortel, EXIN and so on. View list of all certification exams: All vendors We prepare state-of-the art practice tests for certification exams. You can reach us at any of the email addresses listed below. Sales: sales@certsout.com Feedback: feedback@certsout.com Support: support@certsout.com Any problems about IT certification or our products, You can write us back and we will get back to you within 24 hours.