Learning AI at a Glance

Agent

An AI system that plans and acts toward goals, often with tools.

Artificial Intelligence

Systems that perform tasks that typically require human intelligence.

Deep Learning

ML using multi-layer neural networks.

Embedding

Dense vector representation of content for similarity search.

Fine-tuning

Additional training to adapt a model to a specific domain.

Guardrails

Constraints and filters that keep AI systems safe and on-policy.

Hallucination

Confident but incorrect model output not grounded in facts.

LLM

Large Language Model trained to predict and generate text.

Machine Learning

Algorithms that learn patterns from data to make predictions.

Prompt

Input instructions and context given to a generative model.

RAG

Retrieval-Augmented Generation — retrieve context then generate.

Temperature

Sampling parameter controlling randomness of generation.

Token

A unit of text processed by language models.

Transformer

Neural architecture based on self-attention.

Vector Database

Database optimized for storing and searching embeddings.