Lesson 2b System Prompt | Module 2

Lesson 2b: System Prompt with Anthropic Claude

System prompts define Claude's role, personality, and behavior. Learn how Anthropic handles system prompts differently from OpenAI.

Key Difference from OpenAI

OpenAI: System prompt is part of the messages array

messages: [
  { role: "system", content: "You are a helpful assistant" },
  { role: "user", content: "Hello" }
]

Anthropic: System prompt is a separate top-level parameter

system: "You are a helpful assistant",
messages: [
  { role: "user", content: "Hello" }
]

Code Example

Create src/anthropic/basic-prompt-with-system.ts:

import Anthropic from "@anthropic-ai/sdk";
import dotenv from "dotenv";

// Load environment variables
dotenv.config();

// Create Anthropic client with typed configuration
const anthropic = new Anthropic();

// Async function with proper return type
async function basicPromptWithSystem(): Promise<void> {
  try {
    console.log("Testing Anthropic connection...");

    // Make API call - response is automatically typed!
    // Using a system prompt along with user prompt
    const response = await anthropic.messages.create({
      model: "claude-haiku-4-5",
      max_tokens: 1000,
      system: "You are a helpful travel assistant.",  // System prompt here!
      messages: [{ role: "user", content: "Suggest a travel destination" }],
    });

    console.log("✅ Basic Prompt with System Success!");
    // show response usage
    console.log("Tokens used:");
    console.dir(response.usage, { depth: null });

    // Check if we got a response
    if (!response.content || response.content.length === 0) {
      throw new Error("No content in response");
    }

    // Extract text
    const textBlocks = response.content.filter(
      (block) => block.type === "text"
    );

    if (textBlocks.length === 0) {
      throw new Error("No text content in response");
    }

    console.log(
      "AI Response:",
      textBlocks.map((block) => block.text).join("\n")
    );
  } catch (error) {
    // Proper error handling with type guards
    if (error instanceof Anthropic.APIError) {
      console.log("❌ API Error:", error.status, error.message);
    } else if (error instanceof Error) {
      console.log("❌ Error:", error.message);
    } else {
      console.log("❌ Unknown error occurred");
    }
  }
}

// Run the test
basicPromptWithSystem().catch((error) => {
  console.error("Error:", error);
});

Run It

pnpm tsx src/anthropic/basic-prompt-with-system.ts

System Prompt Best Practices

1. Be Clear and Specific

Bad:

system: "You help people"

Good:

system: "You are a helpful travel assistant with expertise in European destinations. Provide detailed, practical travel advice."

2. Define Personality and Tone

system: "You are a friendly, enthusiastic travel expert. Use a warm, conversational tone while providing accurate information."

3. Set Constraints

system: "You are a travel assistant. Always include: 1) Destination details 2) Best time to visit 3) Budget estimate. Keep responses under 200 words."

4. Specify Format

system: "You are a travel assistant. Format all responses with clear sections: Overview, Attractions, Practical Tips."

Comparison: With vs Without System Prompt

Without System Prompt

const response = await anthropic.messages.create({
  model: "claude-haiku-4-5",
  max_tokens: 1000,
  messages: [{ role: "user", content: "Suggest a travel destination" }]
});

Response: Generic travel suggestion

With System Prompt

const response = await anthropic.messages.create({
  model: "claude-haiku-4-5",
  max_tokens: 1000,
  system: "You are a budget travel expert specializing in off-the-beaten-path destinations.",
  messages: [{ role: "user", content: "Suggest a travel destination" }]
});

Response: Budget-friendly, unique destination with cost-saving tips

Advanced System Prompts

Multi-Part System Prompts

system: `You are a professional travel assistant with the following guidelines:

**Expertise:**
- European destinations
- Budget travel tips
- Cultural experiences

**Response Format:**
1. Destination name and location
2. Why visit (2-3 sentences)
3. Best time to visit
4. Estimated budget
5. Top 3 attractions

**Tone:** Friendly, informative, and encouraging`

Role-Based System Prompts

// Code reviewer
system: "You are an experienced TypeScript developer. Review code for best practices, potential bugs, and performance issues."

// Creative writer
system: "You are a creative writing coach. Provide constructive feedback on story structure, character development, and prose."

// Technical explainer
system: "You are a patient teacher explaining complex technical concepts to beginners. Use analogies and simple language."

System Prompt vs User Prompt

System Prompt (Persistent Role)

Sets the AI's personality
Defines expertise area
Establishes response format
Stays the same across conversation

User Prompt (Specific Request)

What you want the AI to do
Changes with each message
Specific questions or tasks

Example Conversation

// Persistent system
system: "You are a travel assistant specializing in Europe"

// First user message
messages: [{ role: "user", content: "Suggest a destination in France" }]

// Second user message
messages: [
  { role: "user", content: "Suggest a destination in France" },
  { role: "assistant", content: "..." },
  { role: "user", content: "What about Italy?" }
]

// System prompt affects BOTH responses with European expertise

Key Takeaways

✅ System prompt is a separate system parameter (not in messages)
✅ Use system prompts to define role, personality, and constraints
✅ System prompts persist across the entire conversation
✅ Be specific about tone, format, and expertise

Next Steps

Learn how to control response creativity with temperature!

Next: Lesson 2c - Temperature Control →

Quick Reference

// Minimal system prompt example
const response = await anthropic.messages.create({
  model: "claude-haiku-4-5",
  max_tokens: 1000,
  system: "You are a helpful travel assistant.",
  messages: [{ role: "user", content: "Suggest a destination" }]
});

Module 2 - Lesson 2b: System Prompt with Anthropic