# Why Prompt?

### Overview

A **prompt** is a structured instruction given to an AI system to guide its behavior and generate a specific output. It defines what the AI should do, how it should respond, and the format of the result.

Well-designed prompts are the foundation of reliable and high-quality AI outputs.

***

### Why Prompts Matter

AI systems rely entirely on the clarity and structure of the input they receive. A vague prompt produces vague results. A precise prompt produces accurate, consistent, and useful outputs.

Effective prompts help:

* Reduce ambiguity
* Improve output consistency
* Control response format
* Maintain brand tone and standards
* Minimize repetitive corrections

***

### Components of a Strong Prompt

A high-quality prompt typically includes:

**1. Context**\
Provides background information about the task.

**2. Objective**\
Clearly defines what needs to be generated or achieved.

**3. Constraints**\
Specifies rules such as tone, length, format, or structure.

**4. Output Format**\
Defines how the response should be structured (e.g., bullet points, JSON, markdown).

***

### Example Prompt Structure

```
Role: You are a technical documentation writer.
Task: Generate documentation for a feature.
Tone: Professional and concise.
Format: Markdown with headings.
Length: 300–500 words.
```

This structure reduces guesswork and ensures predictable results.

***

### Types of Prompts

* **Instruction-Based Prompts**\
  Directly tell the AI what to do.
* **Role-Based Prompts**\
  Assign a specific role to guide tone and expertise.
* **Template-Based Prompts**\
  Use reusable structures with dynamic variables.
* **Constraint-Driven Prompts**\
  Define strict formatting or behavioral rules.

***

### Best Practices

* Be specific and explicit
* Avoid ambiguous language
* Define the output format clearly
* Include examples when necessary
* Use reusable variables for scalability
* Test and refine iteratively

***

### Examples

1️⃣ **Basic Prompt (Plain Text)**

```
You are a professional technical writer.
Generate documentation for a user authentication feature.
Keep the tone professional and concise.
Output in Markdown format.
```

2️⃣ **Role + Task Structured Prompt**

```
Role: Senior Software Architect
Task: Explain how JWT authentication works
Audience: Developers
Format: Step-by-step explanation
Length: Short
```

3️⃣ **Prompt with Variables (Reusable Template)**

```
You are an expert {{ROLE}}.

Generate {{CONTENT_TYPE}} for {{FEATURE_NAME}}.

Constraints:
- Tone: {{TONE}}
- Format: {{FORMAT}}
- Length: {{LENGTH}}
```

Example usage:

```
ROLE = Technical Writer
CONTENT_TYPE = documentation
FEATURE_NAME = Payment Integration
TONE = Professional
FORMAT = Markdown
LENGTH = 400 words
```

4️⃣ **JSON Output Controlled Prompt**

```
Generate API documentation.

Return response in this JSON format:
{
  "title": "",
  "description": "",
  "endpoints": []
}
```


---

# 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/why-prompt.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.