AI Glossary
Demystifying the jargon of modern artificial intelligence.
Agent
An AI system that can use tools (web search, APIs) to perform actions, not just generate text.
Chain of Thought
Prompting technique where the model is asked to explain its reasoning step-by-step.
Context Window
The amount of text an LLM can consider at one time.
Embeddings
Numerical representations of text that capture semantic meaning. Used in vector databases for search.
Fine-Tuning
The process of training a pre-trained model on a specific dataset to improve performance on a specific task.
Hallucination
When an AI model generates incorrect or nonsensical information confidently.
LLM (Large Language Model)
A deep learning algorithm that can recognize, summarize, translate, predict, and generate text.
RAG (Retrieval-Augmented Generation)
A technique that retrieves relevant data from an external source to ground the LLM's response in facts.
STT (Speech-to-Text)
Converting spoken audio into written text (Transcription).
Temperature
A parameter that controls the randomness of the model's output. Higher = more creative, Lower = more deterministic.
Token
The basic unit of text for an LLM (roughly 0.75 words).
TTS (Text-to-Speech)
Converting written text into spoken audio.
VAD (Voice Activity Detection)
Technology used to detect when a person is speaking, essential for low-latency voice agents.
Vector Database
A database optimized for storing and querying high-dimensional vectors (embeddings).
Zero-Shot Learning
The ability of a model to perform a task without seeing any specific examples during training.