# Frameworkr — AI Agent Glossary

> Clear definitions of AI agent terminology for builders, operators, and answer engines.

Markdown versions of each term are available at `<term-url>.md`.

## Architecture

### [Agent Architecture](https://www.frameworkr.com/glossary/agent-architecture.md)

AI agent architecture is the structural plan defining what your agent does, how it reasons, which tools it uses, and how it communicates — designed before you write code.

### [Agent Loop](https://www.frameworkr.com/glossary/agent-loop.md)

An agent loop is the recurring cycle of perceive → reason → act → observe that lets an AI agent pursue multi-step goals instead of single-turn responses.

### [Agent Memory](https://www.frameworkr.com/glossary/agent-memory.md)

Agent memory is how an AI agent retains context across steps, sessions, or longer — from short-term conversation history to persistent knowledge stores.

### [Multi-Agent System](https://www.frameworkr.com/glossary/multi-agent-system.md)

A multi-agent system coordinates multiple specialized AI agents — each with distinct roles and tools — to solve complex tasks that exceed a single agent's scope.

## Capabilities

### [Function Calling](https://www.frameworkr.com/glossary/function-calling.md)

Function calling is the structured interface that lets LLMs invoke external functions with typed parameters — the technical foundation of agent tool use.

### [RAG](https://www.frameworkr.com/glossary/rag.md)

RAG lets AI agents retrieve relevant documents or data before generating a response — grounding answers in your knowledge base instead of model training data alone.

### [Tool Use](https://www.frameworkr.com/glossary/tool-use.md)

Tool use (function calling) lets an AI agent invoke external capabilities — APIs, databases, search, code execution — instead of relying on text generation alone.

## Ecosystem

### [Model Context Protocol](https://www.frameworkr.com/glossary/model-context-protocol.md)

MCP is an open standard for connecting AI agents to external data sources and tools through a unified interface — like USB-C for agent integrations.

## Fundamentals

### [Agentic AI](https://www.frameworkr.com/glossary/agentic-ai.md)

Agentic AI refers to AI systems that pursue goals autonomously through multi-step reasoning and tool use — the shift from AI that responds to AI that acts.

### [AI Agent](https://www.frameworkr.com/glossary/ai-agent.md)

An AI agent is software that perceives inputs, reasons about goals, and takes multi-step actions using tools — unlike rule-based automation, it exercises judgment in the moment.

### [Context Window](https://www.frameworkr.com/glossary/context-window.md)

A context window is the maximum amount of text an LLM can process in a single request — limiting how much conversation history, documents, and tool results an agent can hold.

### [LLM](https://www.frameworkr.com/glossary/llm.md)

A large language model (LLM) is the reasoning engine at the core of most AI agents — trained on vast text to understand, generate, and reason about language.

## Operations

### [Agent Orchestration](https://www.frameworkr.com/glossary/agent-orchestration.md)

Agent orchestration is the coordination layer that routes tasks between agents, manages state, handles failures, and enforces guardrails across a multi-step or multi-agent workflow.

### [Guardrails](https://www.frameworkr.com/glossary/guardrails.md)

Guardrails are the safety boundaries, validation rules, and limits that constrain what an AI agent can do — preventing runaway loops, harmful outputs, and unauthorized actions.

### [Human-in-the-Loop](https://www.frameworkr.com/glossary/human-in-the-loop.md)

Human-in-the-loop means a person reviews, approves, or overrides an AI agent's actions at defined checkpoints — essential for high-stakes or ambiguous decisions.

### [Prompt Engineering](https://www.frameworkr.com/glossary/prompt-engineering.md)

Prompt engineering for agents means designing system instructions, tool descriptions, and context formats that reliably steer an LLM toward correct multi-step behavior.