> For the complete documentation index, see [llms.txt](https://coldbox.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://coldbox.ortusbooks.com/getting-started/agentic-development.md).

# Agentic Development

AI-assisted development for ColdBox — CLI tooling, skills, guidelines, MCP servers, and the BoxLang IDE.

ColdBox is built for the agentic era. AI coding agents like Claude Code, GitHub Copilot, Cursor, Codex, and OpenCode can generate entire features, debug complex issues, and refactor at speed — but their effectiveness depends on how well they understand your codebase and framework.

## Why ColdBox for AI Development?

ColdBox's opinionated conventions make it ideal for AI-assisted development. When an agent adds a handler, it knows exactly where it goes. Routes, models, views, and modules follow predictable patterns, so agents generate idiomatic ColdBox code instead of generic guesses.

On top of those conventions, ColdBox ships a complete agent toolkit:

| Tool                                                                                     | What it gives your agent                                                                           |
| ---------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| [**ColdBox CLI AI**](/getting-started/agentic-development/coldbox-cli-ai-setup.md)       | Project-local guidelines, skills, and agent configs via `coldbox ai install`                       |
| [**Skills & Guidelines**](/getting-started/agentic-development/skills-and-guidelines.md) | 200+ task cookbooks from [skills.boxlang.io](https://skills.boxlang.io) plus framework conventions |
| [**cbMCP**](/getting-started/agentic-development/cbmcp.md)                               | Live introspection of your *running* application over MCP (BoxLang only)                           |
| [**BoxLang IDE**](/getting-started/agentic-development/boxlang-ide.md)                   | VS Code tooling with language intelligence and AI integration                                      |

## Quick Start

```bash
# 1. Get the ColdBox CLI
box install coldbox-cli

# 2. Add AI integration to your project (interactive wizard)
coldbox ai install

# 3. Or scaffold a new app with AI baked in
coldbox create app myApp --ai
```

The wizard detects your AI agents, installs framework guidelines and skills into `.agents/`, and wires up MCP documentation servers. Your agent immediately knows ColdBox conventions, BoxLang syntax, and your installed modules.

```bash
# Keep everything in sync as you add modules
coldbox ai refresh
```

## The Four Pillars

1. **Guidelines** — ColdBox, BoxLang, and CFML conventions stored on-disk in `.agents/guidelines/`, kept lean so agents load them on demand
2. **Skills** — step-by-step implementation cookbooks (build a CRUD handler, a REST API, a test suite) sourced from the central registry
3. **Agents** — ready-made configurations for Claude, Copilot, Cursor, Codex, Gemini, Kilo Code, OpenCode, and Pi
4. **MCP Servers** — 30+ documentation servers auto-matched to your installed modules, plus live app introspection via cbMCP

## See Also

* [AI Runtime Capabilities](/ai/ai.md) — `toAi()`, `toMCP()`, `toAiGateway()`, and BoxLang AI for building AI *features* (as opposed to AI-assisted development)
* [ColdBox CLI](/getting-started/coldbox-cli.md) — the full CLI reference


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://coldbox.ortusbooks.com/getting-started/agentic-development.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.