# 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/>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://codedthemes.gitbook.io/mantis/ai/agents-md.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.