import anthropicclient = anthropic.Anthropic()response = client.messages.create( model="claude-3-5-sonnet-20241022", max_tokens=2048, system="You are a seasoned data scientist at a Fortune 500 company.",# <-- 角色提示 messages=[{"role":"user","content":"Analyze this dataset for anomalies: <dataset>{{DATASET}}</dataset>"}])print(response.content)
Analyze this software licensing agreement for potential risks: <contract> {{CONTRACT}} </contract>
Focus on indemnification, liability, and IP ownership.
Assistant
以下是軟體授權協議的重點摘要:
1. 賠償條款(第 8 節): - 我們對因使用而產生的索賠向供應商作出賠償。
2. 責任限制(第 9 節): - 損害賠償上限為 500 美元。
3. 智慧財產權所有權(第 12 節): - 我們保留對我們修改部分的所有權。
整體而言,協議看起來很標準。賠償和責任條款很典型,我們也保留了智慧財產權。
有了角色設定,Claude 能發現可能造成數百萬損失的關鍵問題:
角色
內容
User
You are the General Counsel of a Fortune 500 tech company. We’re considering this software licensing agreement for our core data infrastructure: <contract> {{CONTRACT}} </contract>
Analyze it for potential risks, focusing on indemnification, liability, and IP ownership. Give your professional opinion.