Short definitions for vocabulary used throughout the TechClub path.

AI and robotics glossary

Term	Student-friendly meaning
Algorithm	A repeatable set of steps for solving a problem.
Agentic AI	An AI application that works toward a goal through multiple steps, tools, observations, and permissions.
API	A defined way for one program to request data or actions from another program.
Bias	A systematic tendency that makes a result unfair or unrepresentative.
Dataset	A collection of examples or measurements used for analysis or learning.
Embedding	A numerical representation that places similar items near one another.
Feature	An input value used by a machine-learning model.
Generative AI	AI that creates or transforms content such as text, images, audio, video, or code.
Hybrid AI	A system that combines different techniques, such as rules, machine learning, retrieval, and language models.
Inference	Using a trained model to produce a prediction or output.
Label	The target answer associated with a training example.
Loss	A number describing how far a model’s prediction is from the desired answer.
Model	A program or mathematical structure that maps inputs to outputs.
Overfitting	Memorizing training examples instead of learning patterns that generalize.
Prompt	Instructions and context supplied to a generative model.
Predictive AI	AI that estimates a label, number, probability, ranking, or other defined target.
Retrieval-augmented generation	Finding relevant source text and providing it to a model before generating an answer.
Sensor	A device that measures something about the world.
Token	A piece of text processed by a language model.
Training	Adjusting model parameters using examples.
Validation	Checking choices during development without using the final test set.
Vector	An ordered list of numbers representing a quantity or features.

Return to the curriculum overview whenever a term is unfamiliar.