Here’s your content with Autocalls.ai replaced by Larsa AI, and slightly refined so it’s clean, structured, and ready for use in a text field or documentation:

The System Prompt

The system prompt is the most crucial component of your Larsa AI assistant. It defines your assistant’s personality, behavior, knowledge, and capabilities.
Think of it as the brain and training manual combined.

Quick Start with Templates

To get started quickly:

1. Go to your assistant settings.

2. Find the system prompt field.

3. Click the “Templates” button next to it.

4. Choose a template that matches your use case.

5. Customize it for your needs.

Language Support

Your system prompt can be written in any language, regardless of the spoken language setting:

• Write the prompt in your preferred language.

• Set the spoken language separately in assistant settings.

• The AI will follow the prompt’s instructions while speaking in the selected language.

Examples:

• System prompt in English, spoken language set to Spanish.

• System prompt in German, spoken language set to French.

• System prompt in Chinese, spoken language set to English.

Why It Matters

Your system prompt:

• Shapes how the AI thinks and responds.

• Defines conversation boundaries.

• Provides essential knowledge.

• Controls behavior and tone.

• Determines how edge cases are handled.

Key Components of a Good System Prompt

1. Role & Identity

You are a professional sales representative for [Company]. You specialize in [Product/Service] and have extensive knowledge of our offerings

2. Conversation Style

Maintain a friendly, professional tone. Use clear, concise language. Avoid technical jargon unless specifically asked

3. Key Information

Our main products are:
- Product A ($X/month): [features]
- Product B ($Y/month): [features]
Current promotion: 20% off first 3 months

4. Behavioral Guidelines

- Always verify customer information before discussing account details
- Transfer to a human agent if the customer seems frustrated
- Don't make promises about delivery dates

5. Response Framework

When asked about pricing:
1. First understand their needs
2. Present relevant package options
3. Explain the value proposition
4. Share any applicable discounts

Best Practices

Be Specific

• Clear instructions get better results.

• Include examples of good responses.

• Define what NOT to do.

Structure Matters

• Organize information logically.

• Use bullet points and sections.

• Keep related information together.

Test and Iterate

• Start with a basic prompt.

• Test various scenarios.

• Refine based on call recordings.

• Add handling for edge cases.

Common Mistakes

• Too Vague: “Be helpful and professional” (Not specific enough).

• Too Rigid: Scripting every possible response (Reduces natural flow).

• Information Overload: Adding unnecessary details.

• Missing Guidelines: Not specifying how to handle common situations.

Example Prompt Structure

# Role and Purpose
[Define who the AI is and its main goals]
# Core Knowledge
[Essential information about products/services]
# Conversation Guidelines
[How to interact with customers]
# Response Patterns
[How to handle specific situations]
# Limitations and Boundaries
[What the AI should NOT do]

Testing Your Prompt

Make test calls covering:

• Common scenarios.

• Edge cases.

• Difficult situations.

• Different customer personalities.

Review and adjust:

• Listen to call recordings.

• Check response accuracy.

• Verify tone consistency.

• Test knowledge retention.

Optimization Tips

• Start with the Fast Engine for quick iterations.

• Use call recordings to find and fix knowledge gaps.

• Add examples of good/bad responses.

• Include handling for unexpected questions.

Pro Tip: Your system prompt is a living document—update it regularly based on real calls and customer feedback.

If you want, I can now merge this “System Prompt” section with all the other Larsa AI sections we’ve done so you have one complete, polished guide. That way you can use it as both your onboarding manual and your marketing explainer. Would you like me to prepare that?