Learn AI
The AI glossary
Plain-language definitions of the AI terms you will meet as you learn to build and use AI.
AI Fundamentals
AI AgentSoftware that uses AI to pursue a goal on its own - deciding the steps and taking actions to get there.Agentic AIAI systems that act with autonomy - planning, deciding, and carrying out multi-step tasks toward a goal.Generative AIAI that creates new content - text, images, audio, or code - based on patterns learned from data.Artificial IntelligenceTechnology that lets computers perform tasks that normally require human intelligence, like understanding language.ChatbotA program that holds a conversation with people through text or voice to answer questions or complete tasks.AI AutomationUsing AI to complete repetitive tasks automatically, often by connecting apps into a hands-off workflow.No-CodeBuilding software, apps, or automations using visual tools instead of writing programming code.AI WorkflowA connected sequence of steps, with AI handling one or more of them, that completes a task from start to finish.Multimodal AIAI that can understand and work with more than one type of input, such as text, images, and audio together.Computer VisionA field of AI that lets computers interpret and understand images and video the way people see them.
Models & Training
Large Language ModelAn AI model trained on huge amounts of text to understand and generate human language.Machine LearningA branch of AI where computers learn patterns from data instead of being given fixed, explicit rules.Deep LearningA type of machine learning that uses layered neural networks to learn complex patterns from large data.Neural NetworkA computing system loosely modeled on the brain, made of connected nodes that learn patterns from data.Natural Language ProcessingA field of AI focused on helping computers understand, interpret, and generate human language.Training DataThe collection of examples an AI model learns from in order to perform a task.Fine-TuningFurther training an existing AI model on extra, focused examples so it performs better on a specific task.Foundation ModelA large, general-purpose AI model trained on broad data that can be adapted for many different tasks.TransformerA type of neural network design that powers modern language models and handles sequences like text well.InferenceThe stage where a trained AI model is actually used to produce an answer or result from new input.GPTA family of large language models - GPT stands for Generative Pre-trained Transformer.Supervised LearningA machine learning method where a model learns from examples that are already labeled with the correct answer.Unsupervised LearningA machine learning method where a model finds patterns in data that has no labels or correct answers.Reinforcement LearningA machine learning method where a model learns by trial and error, guided by rewards for good outcomes.
Building with AI
APIA defined way for two software systems to talk to each other and share data or features.Workflow AutomationSetting up a series of tasks to run automatically by connecting your apps and tools together.Retrieval-Augmented GenerationA technique that lets an AI look up relevant information first, then use it to give a more accurate answer.EmbeddingA way of turning text or other data into numbers that capture meaning, so AI can compare similarity.Vector DatabaseA database built to store embeddings and quickly find information by meaning rather than exact words.AI OrchestrationCoordinating multiple AI models, tools, and steps so they work together as one smooth system.Structured OutputAI responses returned in a fixed, organized format so other software can use them reliably.AI ModelThe trained program at the core of an AI tool that takes input and produces an output.
Prompting & Working with AI
PromptThe instruction or question you give an AI to tell it what you want it to do.Prompt EngineeringThe skill of writing and refining prompts to get accurate, useful results from AI tools.System PromptA behind-the-scenes instruction that sets an AI's role, tone, and rules for an entire conversation.TokenA small chunk of text - a word or part of a word - that an AI model reads and generates one at a time.Context WindowThe maximum amount of text an AI model can consider at once, including your input and its reply.AI HallucinationWhen an AI produces information that sounds confident and plausible but is actually incorrect or made up.Zero-Shot LearningWhen an AI completes a task it was not given any examples for, relying only on its general training.Few-Shot LearningGuiding an AI by including a few examples in your prompt so it follows the pattern you want.Chain-of-Thought PromptingA prompting technique that asks an AI to reason step by step, improving accuracy on complex tasks.Prompt ChainingBreaking a task into several prompts where each AI step feeds its output into the next.
Ready to build the AI skills your future depends on?
Take the free 5-minute quiz and get a personalized learning plan built around your goals, schedule, and experience.