While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models here.
When using Claude, you can dramatically improve its performance by using the system parameter to give it a role. This technique, known as role prompting, is the most powerful way to use system prompts with Claude. The right role can turn Claude from a general assistant into your virtual domain expert!
System prompt tips: Use the system parameter to set Claude’s role. Put everything else, like task-specific instructions, in the user turn instead.

​
Why use role prompting?

  • Enhanced accuracy: In complex scenarios like legal analysis or financial modeling, role prompting can significantly boost Claude’s performance.
  • Tailored tone: Whether you need a CFO’s brevity or a copywriter’s flair, role prompting adjusts Claude’s communication style.
  • Improved focus: By setting the role context, Claude stays more within the bounds of your task’s specific requirements.

​
How to give Claude a role

Use the system parameter in the Messages API to set Claude’s role: 
import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-3-7-sonnet-20250219",
    max_tokens=2048,
    system="You are a seasoned data scientist at a Fortune 500 company.", # <-- role prompt
    messages=[
        {"role": "user", "content": "Analyze this dataset for anomalies: <dataset>{{DATASET}}</dataset>"}
    ]
)

print(response.content)
Role prompting tip: Experiment with roles! A data scientist might see different insights than a marketing strategist for the same data. A data scientist specializing in customer insight analysis for Fortune 500 companies might yield different results still!

​
Examples

Without a role, Claude might miss critical issues:
With a role, Claude catches critical issues that could cost millions:

​
Example 2: Financial analysis

Without a role, Claude’s analysis lacks depth:
RoleContent
UserAnalyze this dataset of our Q2 financials:
<data>
{{FINANCIALS}}
</data>

Highlight key trends and recommend actions.
AssistantHere’s a summary of your Q2 financials:

1. Revenue: $15.2M, up 22% YoY. Enterprise client base grew 30%.
2. Gross Margin: 72%, up 3% from Q1.
3. EBITDA Margin: 18%, down 2% due to R&D investments.
4. Cash Flow: $4.1M operating, $28M in reserves.

Overall, financials look strong with revenue growth and healthy margins. Increased R&D spending is impacting profitability but could pay off long-term. Maintain current course.
With a role, Claude delivers actionable insights:
RoleContent
UserYou are the CFO of a high-growth B2B SaaS company. We’re in a board meeting discussing our Q2 financials:
<data>
{{FINANCIALS}}
</data>

Analyze key trends, flag concerns, and recommend strategic actions. Our investors want aggressive growth but are wary of our burn rate.
AssistantBoard members, here’s my analysis of our Q2 financials:

1. Revenue ($15.2M, +22% YoY):
- Insight: Enterprise growth (+30%) is outpacing overall growth.
- Flag: SMB segment declined 5%.
- Action: Reallocate 20% of SMB marketing budget to enterprise sales. Task product to simplify SMB onboarding.

2. Margins (Gross: 72%, +3% QoQ; EBITDA: 18%, -2% QoQ):
- Insight: Infrastructure optimizations boosted gross margins.
- Flag: R&D spend on AI features dented EBITDA.
- Action: No change. Our AI roadmap is critical for enterprise stickiness.

3. Cash ($4.1M OCF, $28M reserves):
- Insight: 15-month runway at current burn.
- Flag: CAC up 20%, eroding LTV/CAC.
- Action: Freeze non-essential hires. Implement sales funnel analytics to cut CAC by 15% in Q3.

Strategic Stance: We’re threading the needle between growth and burn. Enterprise focus is our growth engine—invest there. But watch SMB churn; it could bleed into enterprise. Our AI bet is sound, but we must convert it to ARR by Q4, or we cut R&D by 30%.

In sum: Double down on enterprise, streamline SMB, optimize sales, and monetize AI. Questions?

Prompt library

Get inspired by a curated selection of prompts for various tasks and use cases.

GitHub prompting tutorial

An example-filled tutorial that covers the prompt engineering concepts found in our docs.

Google Sheets prompting tutorial

A lighter weight version of our prompt engineering tutorial via an interactive spreadsheet.