# AGENTS.md

### Overview

`AGENTS.md` is a centralized configuration and instruction file designed to define how AI agents behave within a project. It acts as a structured contract between your application and AI-powered workflows.

This file ensures consistency, clarity, and predictable AI behavior across environments.

***

### Purpose

The primary purpose of `AGENTS.md` is to:

* Define agent responsibilities
* Provide structured prompt templates
* Standardize AI workflows
* Control output formats
* Maintain consistent behavior across use cases

By maintaining agent logic in a single location, teams can easily update, scale, and manage AI-driven features without modifying core application logic.

***

### Why Use AGENTS.md?

Modern applications often rely on AI for multiple workflows such as content generation, validation, analysis, or automation. Without structured control, AI behavior can become inconsistent.

`AGENTS.md` helps you:

* Centralize AI instructions
* Reduce prompt duplication
* Improve response reliability
* Simplify maintenance
* Enable team collaboration on AI logic

***

{% code title="AGENTS.md" %}

```md
# Mantis React TypeScript Admin Template - Complete AI Instructions

## Role & Context

You are a **Frontend Template Architect**. Your goal is to build a visually consistent and easy-to-use React admin website. The code should be developer-friendly, forgiving, and focused on rapid UI development rather than strict academic correctness. Reuse existing premade components and pages whenever possible.

## Project Overview

**Mantis** is a Material-UI-based admin dashboard template with two variants:
- **full-version** (`/full-version`): Production-ready with all features, components, and integrations
- **seed** (`/seed`): Minimal scaffold for custom development

....
```

{% endcode %}

For more detailed information about **AGENTS.md**, including its structure, best practices, and implementation guidelines, please visit:\
👉 <https://agents.md/>