Explanation:

Reference:
https://docs.microsoft.com/en-gb/azure/cognitive-services/qnamaker/concepts/data-sources-and-content
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/choose-natural-language-processing-service QnA maker conversational AI service and has nothing to do with SQL database You can easily create a user support bot solution on Microsoft Azure using a combination of two core technologies:
- QnA Maker. This cognitive service enables you to create and publish a knowledge base with built-in natural language processing capabilities.
- Azure Bot Service. This service provides a framework for developing, publishing, and managing bots on Azure.
https://docs.microsoft.com/en-us/learn/modules/build-faq-chatbot-qna-maker-azure-bot-service/2-get-started- qna-bot LUIS is used to understand user intent from utterances.
Creating a language understanding application with Language Understanding consists of two main tasks. First you must define entities, intents, and utterances with which to train the language model - referred to as authoring the model. Then you must publish the model so that client applications can use it for intent and entity prediction based on user input.
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/choose-natural-language-processing-service

The correct answers are A. Grounding data can be used to constrain the output of the chatbot and C. The chatbot might respond with inaccurate data.
According to the Microsoft Azure AI Fundamentals (AI-900) study material and Microsoft Learn modules on Azure OpenAI, a chatbot built with Azure OpenAI GPT-3.5 is a large language model (LLM) capable of generating natural language responses. However, these models operate based on statistical patterns learned from massive text datasets-they do not inherently guarantee factual accuracy. Hence, while GPT-based models can produce highly coherent text, they may sometimes generate inaccurate, outdated, or fabricated information (commonly referred to as "hallucinations"). This makes C correct.
Grounding data, as described in Microsoft's Responsible AI and Azure OpenAI grounding documentation, refers to integrating trusted external data sources-such as company documents, databases, or knowledge bases-into the prompt context. This helps the model stay aligned with factual or domain-specific content, effectively constraining its output to be relevant and verifiable. Therefore, A is also correct.
Options B and D are incorrect because GPT models do not always provide accurate information, and they are not approved for critical use cases such as medical diagnosis. Microsoft's Responsible AI principles explicitly prohibit unverified use in healthcare or other high-risk domains.
Thus, the verified answers are A and C.

Explanation:

According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module "Describe features of natural language processing (NLP) workloads on Azure," Natural Language Processing refers to the branch of AI that enables computers to interpret, understand, and generate human language. One of the main NLP workloads identified by Microsoft is speech-to-text conversion, which transforms spoken words into written text.
Creating a text transcript of a voice recording perfectly fits this definition because it involves converting audio language data into text form - a process handled by speech recognition models. These models analyze the acoustic features of human speech, segment phonemes, identify words, and produce a text transcript. On Azure, this function is implemented using the Azure Cognitive Services Speech-to-Text API, part of the Language and Speech services.
Let's examine the other options to clarify why they are incorrect:
* Computer vision workload: Involves interpreting and analyzing visual data such as images and videos (e.g., object detection, facial recognition). It does not deal with speech or audio.
* Knowledge mining workload: Refers to extracting useful information from large amounts of structured and unstructured data using services like Azure Cognitive Search, not transcribing audio.
* Anomaly detection workload: Involves identifying unusual patterns in data (e.g., fraud detection or sensor anomalies), unrelated to language or speech.
In summary, when a system creates a text transcript from spoken audio, it is performing a speech recognition task-classified under Natural Language Processing (NLP). This workload helps make spoken content searchable, analyzable, and accessible, aligning with Microsoft's Responsible AI goal of enhancing accessibility through language understanding.

In the Microsoft Azure AI Fundamentals (AI-900) curriculum, language modeling is described as a core component of Natural Language Processing (NLP) that enables an AI system to understand, interpret, and generate human language in context. The AI-900 Microsoft Learn module "Identify features of Natural Language Processing workloads" explains that language modeling is used to analyze user input and determine intent - essential for conversational systems like chatbots.
In this question, the chatbot must:
* Accept customer orders.
* Retrieve support documents.
* Retrieve order status updates.
All these tasks require the bot to understand user intent and context from text input. This understanding process is driven by language modeling, which predicts meaning and structure within sentences, enabling the system to decide what action to take next.
Microsoft Learn distinguishes between various NLP techniques:
* Sentiment analysis detects emotional tone (positive/negative/neutral).
* Translation converts text between languages.
* Named Entity Recognition (NER) identifies specific entities like names or dates.However, none of these individually allow a system to process commands, requests, or user intents - that capability is part of language modeling, which powers LUIS (Language Understanding Intelligent Service) or the modern Azure Cognitive Service for Language.
Therefore, to build a chatbot that can interpret commands and respond contextually - such as processing orders or retrieving documents - you must use language modeling.

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.