Microsoft AI-900 Dumps for Microsoft Azure AI Fundamentals - Pass in First Attempt 2026

In Azure OpenAI Service, model behavior during text or chat generation is controlled by several parameters, such as temperature, max tokens, top_p, presence penalty, and frequency penalty. According to Microsoft Learn's documentation for Azure OpenAI GPT models, the presence penalty influences how likely the model is to introduce new or diverse tokens in its responses.

Specifically, the presence penalty discourages the model from repeating previously used tokens, encouraging it to explore new topics or ideas instead of sticking to existing ones. Increasing the presence penalty value typically results in more diverse and creative outputs, while lowering it makes responses more repetitive or focused.

Option analysis:

A . Max response (Max tokens): Controls the maximum length of the generated response, not its diversity.

B . Past messages included: Defines how much chat history the model considers for context; it doesn't affect diversity directly.

C . Presence penalty: Encourages novelty and introduces new tokens---this is correct for increasing response variety.

D . Stop sequence: Specifies a sequence of characters or tokens where the model should stop generating output.

According to the AI-900 study guide and Microsoft Learn module ''Identify features of natural language processing workloads'', Natural Language Processing (NLP) enables computers to understand, interpret, and generate human language. Tasks such as extracting key terms, summarizing documents, identifying topics, or determining sentiment fall under NLP workloads.

In this question, you have insurance claim reports stored as text, and you need to extract key terms to generate summaries. This matches the Text Analytics service in Azure Cognitive Services, which uses NLP techniques such as key phrase extraction to identify important concepts within textual data.

The other options are incorrect because:

A . Conversational AI focuses on chatbots or dialogue systems.

B . Anomaly detection identifies unusual data patterns, not textual meaning.

D . Computer vision processes image or video content, not text.

Therefore, extracting key terms from documents is a clear example of Natural Language Processing.

According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module ''Extract insights from text with the Text Analytics service'', key phrase extraction is a feature of the Text Analytics service that identifies the most important words or phrases in a given document. It helps summarize the main ideas by isolating significant concepts or terms that describe what the text is about.

In this scenario, the goal is to determine which documents share similar topics or themes. By extracting key phrases from each document (for example, ''policy renewal,'' ''coverage limits,'' ''claim process''), you can compare and categorize documents based on overlapping keywords. This is exactly how key phrase extraction is used---to summarize and group text content by topic relevance.

The other options do not fit this use case:

A . Translation uses the Translator service, not key phrase extraction.

B . Generating video captions involves speech recognition and computer vision.

C . Identifying sentiment relates to sentiment analysis, not key phrase extraction.

According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Responsible AI Framework, Inclusiveness is one of the six guiding principles for responsible AI. The principle of inclusiveness ensures that AI systems are designed to empower everyone and engage people of all abilities. Microsoft emphasizes that inclusive AI systems must be developed with awareness of potential barriers that could unintentionally exclude certain user groups. This directly aligns with the scenario described---where the company is examining voice recognition technologies in smart home devices to identify barriers that might leave out users, such as those with speech impairments, accents, or language differences.

The official Microsoft Learn module ''Identify guiding principles for responsible AI'' explains that inclusiveness focuses on creating systems that can understand and serve users with diverse needs. For example, voice recognition models should account for variations in dialect, tone, accent, and speech patterns to ensure equitable access for all. A lack of inclusiveness could cause bias or misrecognition for underrepresented groups, leading to unintentional exclusion.

Microsoft's guidance further stresses that designing for inclusiveness involves involving diverse users in the data collection and testing phases, conducting accessibility assessments, and continuously improving model performance across different demographic groups. In this way, inclusiveness promotes fairness, accessibility, and usability across cultural and physical differences.

In contrast:

A . Accountability is about ensuring humans are responsible for AI outcomes.

B . Fairness focuses on preventing bias and discrimination in data or algorithms.

D . Privacy and security ensure protection of personal data and secure handling of information.

Thus, evaluating potential barriers that could exclude specific user groups exemplifies Inclusiveness, as it demonstrates a proactive approach to making AI accessible and beneficial for all users.

What is a Predicted vs. True chart?

Predicted vs. True shows the relationship between a predicted value and its correlating true value for a regression problem. This graph can be used to measure performance of a model as the closer to the y=x line the predicted values are, the better the accuracy of a predictive model.

https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-m