Azure AI Fundamentals (AI-901) key terms

The field of building computer systems that perform tasks normally requiring human intelligence, such as understanding language, recognizing images, making decisions, or generating content.

A branch of AI in which systems learn patterns from data and improve with experience, rather than following rules written by hand for every case.

A machine learning approach that stacks many layers of artificial neurons so the system can learn complex patterns such as speech, images, and language directly from raw data.

A computing structure of connected nodes arranged in layers, loosely inspired by the brain, that transforms input values step by step to produce a prediction or generated output.

The trained artifact produced by a machine learning process. It holds learned parameters and turns new input data into predictions, classifications, or generated content.

The labeled or unlabeled examples used to teach a model. Its quality, size, and representativeness strongly shape how accurate and fair the finished model becomes.

A training method that uses examples paired with known correct answers, so the model learns to map inputs to expected outputs such as categories or numeric values.

A training method that works with data having no known answers, seeking hidden structure such as natural groupings or unusual records within the dataset.

A supervised task that assigns each input to one of a fixed set of categories, for example labeling a message as spam or not spam.

A supervised task that predicts a continuous numeric value, such as a price, temperature, or expected demand, instead of a discrete category.

An unsupervised technique that groups similar records together based on shared characteristics, without being told in advance what the groups should be.

The AI capability that lets systems interpret images and video, supporting tasks such as detecting objects, reading text, classifying scenes, or recognizing faces.

The AI capability concerned with understanding and producing human language, covering tasks such as sentiment analysis, translation, summarization, and question answering.

AI that creates new content such as text, images, audio, or code by learning patterns from large amounts of existing data and producing novel combinations on request.

A generative model trained on very large text collections to predict and produce language, enabling chat, summarization, translation, and code generation.

A large pretrained model that serves as a general base for many downstream tasks, typically adapted through prompting or fine-tuning rather than trained from scratch.

A model that accepts or produces more than one kind of content, such as combining text and images in a single request or response.

The instruction or input text a person sends to a generative model. Its wording, context, and examples strongly influence the quality of the response.

A small chunk of text, roughly a word fragment, that language models process as units. Token counts drive context limits and usage-based billing.

A confident but incorrect or fabricated output from a generative model, often occurring when the model lacks reliable information and fills gaps with plausible-sounding content.

A set of principles guiding AI development, commonly fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability, so systems treat people justly.

Microsoft's platform for building, evaluating, deploying, and governing AI applications and agents, bringing together model access, tools, and project resources in one place.

A workspace within Microsoft Foundry that groups related models, connections, agents, evaluations, and other resources for a single AI solution.

A browsable library of pretrained models inside Microsoft Foundry, spanning providers and modalities, from which teams can select, test, and deploy a model.

The act of publishing a model to an endpoint so applications can send requests to it. Settings include capacity, rate limits, and the deployment name used in calls.

A network address and credential pair that an application calls to reach a deployed model or service, typically secured with a key or Microsoft Entra ID authentication.

An interactive area in Microsoft Foundry for trying prompts and model settings against a deployed model before writing application code around it.

Instructional text sent ahead of user input that sets a model's role, tone, and boundaries, helping keep responses consistent across a conversation.

A model setting that controls randomness in generated output. Lower values make responses more predictable and focused; higher values make them more varied and creative.

The maximum amount of text, measured in tokens, that a model can consider at once, covering the prompt, any supplied documents, and the generated reply.

A pattern that retrieves relevant content from a data source and adds it to the prompt, so answers rely on supplied facts rather than only on the model's training.

Anchoring model responses in trustworthy, supplied information such as company documents or search results, which reduces invented answers and improves relevance.

A numeric vector representing text or another item so that similar meanings sit close together, enabling semantic search, recommendations, and retrieval in RAG solutions.

A retrieval method that finds items whose stored embeddings are most similar to a query embedding, powering semantic lookup over documents, images, or other content.

Further training of an existing model on a smaller, task-specific dataset so its behavior better matches a particular domain, style, or set of examples.

An AI component that pursues a goal by reasoning over a request, choosing and calling tools or knowledge sources, and returning a result, often across multiple steps.

A function or external service an agent or model can invoke, such as a search index, calculator, or business API, to obtain information or perform actions beyond text generation.

A model capability where the model returns a structured request to run a named function with specific arguments, letting the application execute code and feed results back.

The practice of measuring a model or application's quality using metrics and test datasets, such as groundedness, relevance, coherence, and similarity to expected answers.

Filtering that detects and blocks harmful categories such as hate, violence, sexual content, and self-harm in prompts and responses, with configurable severity thresholds.