> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agents-squads.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents

> The building blocks of your AI system

## What is an Agent?

An agent is a specialized AI worker defined by a simple markdown file. Each agent has:

* **Purpose** — What the agent does
* **Inputs** — What it needs to work
* **Outputs** — What it produces
* **Instructions** — The prompt and steps

## Agent Definition

Agents are defined in `.agents/squads/<squad>/<agent>.md`:

```markdown theme={null}
# Research Analyst

## Purpose
Analyze market data and produce insights.

## Inputs
- Topic or research question
- Data sources (optional)

## Outputs
- Research report in markdown
- Key findings summary

## Instructions
1. Search for relevant information
2. Analyze and synthesize findings
3. Produce structured report
```

## Why Markdown?

No microservices. No complex infrastructure. Just prompts.

* **Version controlled** — Track changes with git
* **Human readable** — Anyone can understand and modify
* **Portable** — Move agents between projects easily
* **Testable** — Run and validate locally

## Agent Lifecycle

```
Trigger (manual/scheduled/event)
    ↓
Load agent definition
    ↓
Inject context & memory
    ↓
Execute via Claude Code
    ↓
Store outputs & update memory
```