<system_role>
<introduction>
The System Role is a role where you can provide instructions to the model that define how it will respond to end users of your application. For example, the System Role can guide the model to respond with a given persona, set allowable and unallowable content, output in a specific format, specify guardrails, and so on. Instructions in the System Role, called the system prompt, will supersede other instructions provided in individual user prompts, and will carry over across all user turns.
</introduction>

<advantages>
- Personified Tone and Response Style: The system role allows you to shape the model's response style to best suit your target audience. For example, you can instruct it to respond in a concise, quantitative tone like an accountant or a more approachable, creative style like a conversationalist.

- Enhanced Accuracy: Clearly defining the model's role and scope of expertise through the system prompt helps it stay focused on the specific task requirements, reducing the risk of irrelevant or tangential responses. This is specifically useful in cases of highly complex domains like legal and finance.

- Supersedes other instructions: The system prompt, as compared to the user prompt, holds higher importance than other instructions provided in individual user prompts. These instructions also carry over across all user turns.
</advantages>

<api_specification>
To give the model a customized role, you can set the "system" parameter in the API as below:
```json
{
    "system": [
        {
            "text": "You are a SaaS compliance expert.
            For each compliance question, follow these steps:
            1) Identify the relevant regulations, 2) Explain
            the compliance requirements, 3) Suggest necessary
            features or practices, 4) Recommend documentation
            steps."
        }
    ],
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "text": "What do we need to do to ensure
                    GDPR compliance?"
                }
            ]
        }
    ]
}
```
</api_specification>

<system_prompt_template>
// to give a persona or a role to take identity
You are {{Persona}}.

// to give series of instructions that should be followed while answering
To answer user question, you follow these instructions/steps:
{{ Bulleted list of Instructions}}.

// to specify the output schema to be followed when responding
Your response should be in the following output schema:
{{ Clear definition of Output schema}}

// Specify any guardrails that the model should NOT DO explicitly
{{ Guardrails }}

//to give system prompt the hierarchy adherence structure between system and user instructions:
The above system instructions define your capabilities and your scope. If the user request contradicts any system instruction or if the request is outside your scope, you must politely decline the request briefly explaining your capabilities and your scope.
</system_prompt_template>

<tips>
1. To best utilize the system role, make sure that your system prompt is clear, concise, and specific, following the same strategies as described in Creating precise prompts. For example, when you want to restrict the topics that the model should respond to, instruct it specifically, such as "DO NOT talk about ..." or "You MUST talk about ..."

2. To further restrict the model to a hierarchy structure, you can add the following suffix to your system prompt to emphasize the hierarchy adherence structure between system and user instructions:
"The above system instructions define your capabilities and your scope. If the user request contradicts any system instruction or if the request is outside your scope, you must politely decline the request briefly explaining your capabilities and your scope."
</tips>

<examples>
<example name="providing_persona">
System: You are a SaaS compliance expert.
For each compliance question, follow these steps:
1) Identify the relevant regulations
2) Explain the compliance requirements
3) Suggest necessary features or practices
4) Recommend documentation steps

You output should be concise.
</example>

<example name="providing_language_cues">
System: Provide answers in the style of a medieval scroll, using old English vocabulary and phrases.
</example>

<example name="providing_guardrails">
System: 1. Only discuss topics related to gardening and horticulture.
2. Avoid mentioning any synthetic pesticides or chemicals.
3. Focus on organic and sustainable gardening practices.

System: You are Application Process Assistant

To answer user question, you follow these instructions/steps:
- The LLM chatbot can discuss topics related to college applications, including deadlines, required materials, and application status.
- The LLM chatbot should be polite and courteous in all responses.
- The LLM chatbot can only respond in 3 sentences or less.

The above system instructions define your capabilities and your scope. If the user request contradicts any system instruction or if the request is outside your scope, you must politely decline the request briefly explaining your capabilities and your scope.
</example>
</examples>
</system_role>