Large Language Model (LLM)

A Large Language Model (LLM) is an AI model trained on massive amounts of text data, enabling it to understand and generate human-like language.

By leveraging billions of parameters, LLMs can interpret context and perform a wide range of language tasks such as answering questions, summarization, and translation.

In Agentria, LLMs are connected as nodes to serve as intelligent decision-making engines, helping agents understand user inputs and determine next actions.

API

An API (Application Programming Interface) is an interface that allows applications to communicate with one another.

It defines a set of rules and formats for one software system to access the functionality or data of another.

APIs act as standardized channels that connect systems and make their features available for use.

In Agentria, agents rely on APIs to call external services—such as translation tools, payment systems, or third-party integrations.

Through APIs, agents can access external resources and perform richer, more versatile operations.

Workflow

A Workflow is a collection of nodes that automate processes, forming the sequence of tasks an agent carries out.

Multiple nodes are linked together through inputs and outputs, and this flow becomes a complete agent operation.

A workflow is both the execution path that visually models an agent’s logic, and the core structure that modularizes and automates complex processes.

Project

A Project is a container that organizes multiple workflows and their configurations in one place.

Within a project, users can design agents and configure required components such as nodes, abilities, API keys, and environment variables.

Each project runs independently and can be used as a unit for version control, team collaboration, or deployment.

In Agentria, a project is both the workspace for agent development and the execution package for management and distribution.