> For the complete documentation index, see [llms.txt](https://docs.glbnxt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.glbnxt.com/tutorials/guides/building-a-super-system-prompt.md).

# Building a Super System Prompt

### A Practical Guide for AI Power Users

***

### Introduction

When you open a chat interface and start a conversation with an AI model, something invisible is already shaping every response you receive. Before your first message is processed, the model reads a block of instructions that defines who it is, how it should behave, what it knows about you, and what kind of output it should produce. That block of instructions is the system prompt.

Most users never see it. Many never think about it. But for anyone who wants to move beyond casual use and get consistent, high-quality, context-aware results from an AI model, understanding and mastering the system prompt is the single most impactful skill you can develop.

This tutorial is written for users working inside AI-enabled environments like GLBNXT Workspace, where the underlying chat interfaces expose system prompt configuration directly. Whether you are an individual knowledge worker customising your personal assistant, a team lead building a shared configuration for your department, or a developer designing an AI-powered workflow, this guide will give you the conceptual foundation and practical tools to write a system prompt that genuinely performs.

The core argument of this tutorial is simple: a minimal system prompt produces a minimal assistant. A well-crafted, comprehensive system prompt produces a reliable, focused, and capable one. The difference between the two is not a matter of luck or model capability. It is a matter of instruction quality.


---

# 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://docs.glbnxt.com/tutorials/guides/building-a-super-system-prompt.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.
