Free AI-900 sample questions

Correct answer: The Indexing and Retrieval System

In a Retrieval-Augmented Generation (RAG) pattern, the indexing and retrieval system (often a vector database like Azure AI Search) is responsible for searching the source data to find the most relevant information based on the user's query. This retrieved context is then passed to the LLM to generate a grounded response.

Correct answers: Severity levels for content categories; Custom blocklists

Severity levels (e.g., 0-7) allow for fine-grained control over how sensitive the detection is for each category. Setting a low threshold for the 'self-harm' and 'violence' categories makes the filtering more aggressive.

Custom blocklists allow the team to add specific terms, phrases, or patterns that are highly indicative of the content they wish to filter, providing an extra layer of targeted moderation.

Correct answer: False

The Azure AI Foundry model catalog is designed to be comprehensive and includes a wide variety of models, including state-of-the-art open-source models (like those from Hugging Face and Meta), models from Microsoft, and models from OpenAI.

Correct answer: Custom Named Entity Recognition (NER)

Custom Named Entity Recognition (NER) is the ideal feature for this scenario. While standard NER can find general entities like people and places, Custom NER allows the hospital to train a model to recognize specific, domain-relevant entities such as 'medical conditions', 'medications', and 'dosages'.

Correct answer: Azure AI Translator

Azure AI Translator, specifically its Document Translation feature, is designed for this exact purpose. It can translate entire documents or batches of documents in various file formats while preserving the original structure and formatting, which is a key requirement for the news organization.

Correct answer: The user's goal: to check the order status

In conversational AI, the 'intent' represents the user's underlying goal or intention. In this case, the user's goal is to find out the status of their order. The specific question is the 'utterance', and '789123' is an 'entity'.

Correct answer: Fairness

The principle of Fairness is violated. This principle dictates that AI systems should treat all people fairly and avoid affecting similarly situated groups of people in different ways. The model's systemic underperformance for a specific demographic (people in low-income neighborhoods) is a clear example of algorithmic bias and unfairness.

Correct answer: Transparency

Model explanations, which help humans understand the reasoning behind an AI's decisions, are a core component of the Transparency principle. Transparency is about ensuring that AI systems are understandable, and providing tools for interpretability and explainability is key to achieving this.

Correct answer: Anomaly detection

Anomaly detection is the AI workload focused on identifying rare items, events, or observations which raise suspicions by differing significantly from the majority of the data. Examples include fraud detection in credit card transactions or identifying a faulty sensor in an IoT network.

Correct answer: Overfitting

Overfitting occurs when a machine learning model learns the training data too well, including its noise and random fluctuations. This results in a model that performs very well on the training data but fails to generalize to new, unseen data, leading to poor performance on the test set.