Welcome to the next step in your journey of creating a personal tutor with DeepSeek! In the previous lessons, you learned how to send messages to DeepSeek's language model, explored model parameters, and understood the importance of maintaining tutoring session history. Now, we will focus on personalizing your AI tutor by using system prompts. System prompts allow you to define the tutor's personality and expertise, enabling you to customize the behavior and tone of the AI's responses. This lesson will guide you through creating a specialized math and science tutor, demonstrating how system prompts can shape the tutor's interactions.

A system prompt is a key tool for customizing the AI tutor's behavior, setting the stage for how it interacts with students. It acts as a directive that defines the tutor's personality and expertise, guiding its responses to align with a specific teaching style or subject focus. We call it a system prompt because it serves as an overarching instruction to the AI, distinct from user or assistant messages, which are part of the ongoing tutoring session. While user messages are inputs from the student interacting with the tutor, and assistant messages are the tutor's responses, the system prompt is a one-time setup that influences all subsequent interactions within a session.

The system prompt does not persist across multiple sessions; it is reset each time a new session begins. If you change the system prompt mid-session, the AI will immediately adopt the new personality and expertise as defined by the updated prompt. However, for consistency and to avoid confusion, it's generally recommended to set the system prompt at the beginning of a session and maintain it throughout.

Here’s how you can set up a system prompt in Go using the recommended code style:

To illustrate how a system prompt shapes the AI tutor's behavior, let's interact with an AI that has the math and science tutor personality set in our system prompt. When you run the code above, the tutor's response will reflect the experienced math and science tutor personality. The output might look something like this:

This educational response showcases how the system prompt shapes the tutor's interactions, allowing it to respond with clear, concise explanations focused on mathematical concepts — precisely what we defined in our system prompt.

One of the powerful aspects of system prompts is that they can be tailored to create tutors with different specializations or teaching styles. Let's look at how we might create a tutor with a different focus using Go:

Running this code results in an output similar to the following:

In this lesson, you learned how to personalize your AI tutor using system prompts. By defining the tutor's personality and expertise, you can customize its behavior and tone, creating educational interactions tailored to specific subject areas. We walked through an example of building a specialized math and science tutor, demonstrating how system prompts influence the tutor's responses.

As you move on to the practice exercises, experiment with different system prompts to see how they affect the tutor's behavior. This hands-on practice will reinforce what you've learned and prepare you for the next unit, where we'll explore managing multiple tutoring sessions.