AI-901 Exam Dumps - Microsoft Azure AI Fundamentals (Updated Version)

When using the OpenAI Responses API and a vision-enabled model, you can include an image in a request by providing the image as a base64-encoded image data.

Azure OpenAI / Microsoft Foundry vision requests support image input as an input_image item. The image can be provided by URL or as base64-encoded image data in the request. Microsoft documentation for Azure OpenAI batch examples also lists Base64 encoded image and Image URL as supported input patterns for Responses API requests.

The other options are incorrect:

a CSV file attachment is not an image input format for vision analysis.

an MP4 video stream is video content, not an image format.

a shared access signature (SAS) token is only an access token for a protected resource; it is not the image data itself.

To send chat prompts to a deployed model, the application needs authentication credentials, the endpoint URL, and the model deployment name. Microsoft’s Foundry SDK guidance shows authentication with credentials, an endpoint, and the model= " model_deployment_name " value when calling a deployed model.

The correct Python method is:

recognizer.recognize_once()

Completed code:

import azure.cognitiveservices.speech as speechsdk

speech_config = speechsdk.SpeechConfig(subscription=key, region=region)

recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config)

recognizer.recognize_once()

Microsoft’s Azure Speech documentation for Foundry Tools explains that Speech to text is used for real-time speech recognition and converting spoken audio into text. The Python Speech SDK uses a SpeechRecognizer object for recognition from audio input, such as a microphone.

Why the other options are incorrect:

recognizer.speak_text_async( " Ready " ) is incorrect because speaking text is text-to-speech, not speech-to-text recognition.

recognizer.start_continuous_recognition() can be used for continuous recognition, but the code shown is asking for the basic method to recognize spoken input and convert it to text from the SpeechRecognizer.

recognizer.start_keyword_recognition() is used for keyword/wake-word recognition, not general speech-to-text transcription of spoken commands.

Therefore, the correct answer is:

recognizer.recognize_once()

Statement 1: Voice Live returns only transcribed text. = No

Voice Live is not limited to returning transcribed text. It is designed for real-time spoken conversational experiences and can include speech input, model reasoning, and spoken output.

Statement 2: Voice Live requires you to separately implement speech to text and text to speech services. = No

Voice Live combines the conversational voice pipeline, so you do not need to separately build independent speech-to-text and text-to-speech services for the same real-time voice experience.

Statement 3: Voice Live combines speech to text, reasoning, and text to speech into a single conversational experience. = Yes

This statement is correct. Voice Live is used for real-time conversational AI experiences where spoken input is processed, the model reasons over the request, and spoken output can be returned.

The correct answer is A. transparency . In Microsoft’s Responsible AI framework, transparency requires that people can understand relevant aspects of how an AI system was created, how it operates, what information it relies upon, and why it produces particular outcomes. The current Microsoft Azure AI Fundamentals study guide specifically includes “Describe considerations for transparency in an AI solution” under the responsible AI objectives.

Identifying and documenting the source of training data directly supports transparency because it establishes data provenance. Stakeholders can determine where the model’s knowledge originated, assess the appropriateness and limitations of the dataset, investigate potential biases, and better understand factors that may influence model behaviour. Microsoft also describes transparency as helping stakeholders understand how and why AI systems work , with interpretability and information about datasets and model characteristics contributing to trust and auditability.

Privacy and security concerns protecting data and controlling its use. Reliability and safety concerns predictable, robust operation. Fairness focuses on avoiding systematically unequal outcomes across groups. Merely disclosing where training data came from is therefore principally a transparency practice.

Study Guide Reference: Describe principles of responsible AI → Describe considerations for transparency in an AI solution.

Ongoing monitoring, feedback, and evaluation are goals of the Reliability & Safety principle.

The Microsoft responsible AI principle of Reliability and safety focuses on ensuring that AI systems operate consistently, safely, and as intended across different conditions. This includes testing, monitoring, collecting feedback, and evaluating system performance over time.

Why the other options are incorrect:

Human oversight and control aligns more closely with accountability.

Data governance and management aligns more closely with privacy and security.

The minimization of stereotyping, demeaning, and erasing outputs aligns more closely with fairness and inclusiveness.

The completed sentence is:

To define an agent ' s role and behaviors, you must configure a system prompt for the agent.

In Microsoft Foundry / Azure AI agent scenarios, the system prompt, also referred to as system instructions, defines how the agent should behave, what role it should follow, and what constraints it must observe.

The other options are incorrect:

deployment slot relates to hosting/deployment routing, not agent behavior.

embedding index is used for vector search or retrieval scenarios, not defining the agent’s role.

fine tuning job changes or adapts model behavior through training, but it is not the standard configuration used to define an agent’s role and behavior at runtime.

Therefore, the correct answer is system prompt.