用系統訊息控管行為

Claude 模型入門

Nikhil Rangarajan

Data Scientist

什麼是系統訊息？

客服機器人
要求：
- 有禮
- 精簡
- 每則回覆結尾加上「Is there anything else I can help you with today?」

一個機器人

什麼是系統訊息？

系統訊息為 Claude 設定全域行為規則
作用於整段對話，而非單一回覆
控制語氣、限制、輸出格式與人設

一個機器人問「Is there anything else I can help you with today?」

撰寫有效的系統提示

明確描述行為與限制
定義 Claude 應採取的角色

system_msg = "Be helpful." # Weak

system_msg = "You are a technical writer. Use active voice, under 100 words, 
actionable advice only." # Strong


messages = [{"role": "user", "content": "How do I improve documentation?"}]

response = client.messages.create(model="claude-sonnet-4-6", 
max_tokens=150, system=system_msg,  messages=messages)

常見的系統訊息樣式

角色導向：定義 Claude 是誰

$$

限制導向：設定長度或格式限制

$$

語氣導向：控制情緒風格

$$

任務導向：提供專門指示

# Role-based
"You are a customer service rep."

# Constraint-based  
"Respond in exactly 3 bullet points,
max 50 words."

# Tone-based
"Use enthusiastic, encouraging tone."

# Task-specific
"Debug Python code. Always ask for 
error messages first."

測試與迭代系統訊息

用多樣使用者輸入測試以找邊界情況
監測不期望的輸出或行為漂移
需要時細化語句、提高明確度

# System message causing issues
"Be concise and helpful."

# Problem: Responses too short, 
# missing context
"Provide helpful responses in 2-3 
sentences. Include relevant context 
but avoid unnecessary details."

# Test with various prompts

進階系統訊息技巧

$$

結合指示並標明優先順序
以條件邏輯處理情境
在系統訊息內加入範例
搭配 few-shot 提示分層

system_msg = """Code reviewer. 
Priority: 1) Security 2) Performance 
3) Style
If no issues: "Code looks good" 
+ suggest improvement
Example: "Security: No issues. 
Performance: Consider caching here."
"""

messages = [{"role": "system", 
             "content": system_msg},
    {"role": "user", 
     "content": "Review: [code]"}]

一起來練習吧！

Claude 模型入門

Preparing Video For Download...