# Glossary

This document provides a glossary of key terms and concepts used in the ADAM v21.0 technical specification.

## A

*   **Agent:** An autonomous component that is designed to perform a specific task.
*   **Agent Orchestrator:** The component that is responsible for managing the lifecycle of the agents and orchestrating their interactions.
*   **API (Application Programming Interface):** A set of rules and protocols that allows different software applications to communicate with each other.
*   **Autonomous Mode:** A mode of operation in which the system performs tasks without human intervention.

## C

*   **Chatbot:** A computer program that is designed to simulate human conversation.
*   **CI/CD (Continuous Integration/Continuous Deployment):** A set of practices that automate the process of building, testing, and deploying software.
*   **Component:** A self-contained unit of software that provides a specific set of features or functionality.

## D

*   **Data Store:** A general-purpose repository for storing and managing data.
*   **Data Warehouse:** A centralized repository for storing and analyzing large volumes of structured data.
*   **Docker:** A platform that allows you to create, deploy, and run applications in containers.

## E

*   **ETL (Extract, Transform, Load):** A process for moving data from one system to another.

## F

*   **FIBO (Financial Industry Business Ontology):** An industry-standard ontology for the financial services industry.
*   **Financial Digital Twin:** A virtual representation of a financial entity, such as a company or a portfolio.

## H

*   **Human-in-the-Loop:** A mode of operation in which humans are involved in the decision-making process.

## J

*   **JWT (JSON Web Token):** A standard for creating access tokens that are used to authenticate users and authorize access to resources.

## K

*   **Knowledge Base:** A centralized repository of knowledge that is used by the agents to perform their tasks.

## L

*   **LLM (Large Language Model):** A type of artificial intelligence that is trained on a massive amount of text data and can be used to generate human-like text.

## P

*   **Prompt:** A piece of text that is used to guide an LLM in generating a response.
*   **Prompted Mode:** A mode of operation in which the system prompts the user for input at predefined checkpoints in a workflow.

## R

*   **RBAC (Role-Based Access Control):** A method for restricting access to resources based on the user's role.
*   **REST (Representational State Transfer):** An architectural style for designing networked applications.

## S

*   **Schema:** A description of the structure of a database or other data source.
*   **SPA (Single-Page Application):** A web application that loads a single HTML page and then dynamically updates the content as the user interacts with the application.

## T

*   **Token:** A unit of text that is used by an LLM to process and generate language.

## U

*   **User Story:** A short, simple description of a feature told from the perspective of the person who desires the new capability, usually a user or customer of the system.

## W

*   **Workflow:** A sequence of steps that are executed to achieve a specific goal.