AI Glossary
Plain-language definitions for the terms that come up most when planning an AI project.
Machine Learning (ML)
A method of building systems that learn patterns from data rather than following hand-written rules.
Large Language Model (LLM)
A neural network trained on large amounts of text, able to generate and reason about language.
Generative AI
AI systems that create new content (text, images, audio, or code) rather than only classifying or predicting.
MLOps
The practices and tooling used to deploy, monitor, and maintain machine-learning models in production reliably.
Computer Vision
The field of AI focused on extracting information and understanding from images and video.
Natural Language Processing (NLP)
Techniques that let computers understand, interpret, and generate human language.
RAG (Retrieval-Augmented Generation)
An approach where a model retrieves relevant documents at query time to ground its answers in real information.
Fine-tuning
Further training a pre-trained model on a smaller, specific dataset so it performs better on a particular task.
Inference
The process of running a trained model on new input to produce a prediction or output.
Model Drift
The gradual decline in a model's accuracy as real-world data shifts away from what it was trained on.
Agentic AI
AI systems that can plan multi-step actions and use tools autonomously to complete a task, not just answer a single prompt.
Vector Database
A database optimized for storing and searching numerical embeddings, commonly used to power semantic search and RAG.
Data Pipeline
An automated sequence of steps that moves and transforms data from source systems into a usable form for analysis or modeling.
A/B Testing
Comparing two versions of a product or model against real users to see which performs better on a given metric.
Begin
Skip the glossary. Describe your problem and we'll tell you which of these actually applies.