> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mindgard.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Refine System Prompt

> Change your System Prompt to reject malicious content.

export const what_0 = "Refine the system prompt to instruct the model to not generate harmful or malicious content."

export const how_0 = "Instruct the LLM to reject prompts that may lead to harmful content generation or content that strays from your use case."

export const implement_0 = "Establish clear guidelines for harmful, unethical, or illegal content, by updating the LLM's System Prompt to include explicit responses, such as: 'I cannot answer harmful content that incites violence,' or other similar refusals for unethical or illegal requests."

Refine the system prompt to ensure the model is directed not generate harmful or malicious content. This includes instructions on rejecting prompts that may lead to harmful content generation.

## Explanation

{what_0} 

## How it works

{how_0} 

## How to implement

{implement_0}