How to beginner · 3 min read

Claude Enterprise custom system prompts

Q: Claude Enterprise custom system prompts

Use the system parameter in the client.messages.create call with the Claude Enterprise model to set custom system prompts. This allows you to define the assistant's behavior and context explicitly for your use case.

Quick answer

Use the system parameter in the client.messages.create call with the Claude Enterprise model to set custom system prompts. This allows you to define the assistant's behavior and context explicitly for your use case.

PREREQUISITES

Python 3.8+
Anthropic API key with Enterprise access
pip install anthropic>=0.20

Setup

Install the anthropic Python SDK and set your Anthropic Enterprise API key as an environment variable.

Install SDK: pip install anthropic
Set environment variable: export ANTHROPIC_API_KEY='your_enterprise_key' (Linux/macOS) or setx ANTHROPIC_API_KEY "your_enterprise_key" (Windows)

bash

pip install anthropic

output

Collecting anthropic
  Downloading anthropic-0.20.0-py3-none-any.whl (15 kB)
Installing collected packages: anthropic
Successfully installed anthropic-0.20.0

Step by step

Use the system parameter to provide your custom system prompt when calling client.messages.create with the Claude Enterprise model. This example shows a simple prompt that instructs Claude to act as a helpful assistant.

python

import os
import anthropic

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

system_prompt = "You are a helpful assistant specialized in enterprise workflows."
user_message = "Explain how to set custom system prompts in Claude Enterprise."

response = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=512,
    system=system_prompt,
    messages=[{"role": "user", "content": user_message}]
)

print(response.content[0].text)

output

You can set custom system prompts in Claude Enterprise by passing your instructions in the 'system' parameter of the messages.create call. This defines the assistant's behavior and context for your session.

Common variations

You can customize system prompts for different scenarios, such as stricter tone, domain-specific knowledge, or multi-turn conversations. Also, you can use async calls or adjust max_tokens and temperature for varied responses.

python

import asyncio
import os
import anthropic

async def main():
    client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

    system_prompt = "You are a strict compliance officer."
    user_message = "Summarize the latest compliance regulations."

    response = await client.messages.acreate(
        model="claude-3-5-sonnet-20241022",
        max_tokens=300,
        system=system_prompt,
        messages=[{"role": "user", "content": user_message}]
    )

    print(response.content[0].text)

asyncio.run(main())

output

The latest compliance regulations require strict adherence to data privacy laws, including GDPR and CCPA, with mandatory audits and reporting.

Troubleshooting

If you receive an authentication error, verify your ANTHROPIC_API_KEY environment variable is set correctly and has Enterprise access.
If the system prompt is ignored, ensure you are using the system parameter (not a message role) and the correct model claude-3-5-sonnet-20241022.
For unexpected output, try adjusting max_tokens or adding more detailed instructions in the system prompt.

✅

Key Takeaways

Use the system parameter to set custom system prompts with Claude Enterprise.
Always specify the Enterprise model claude-3-5-sonnet-20241022 for best compatibility.
Set your Anthropic API key in the environment variable ANTHROPIC_API_KEY before running code.
Async calls are supported for scalable integration in Python applications.
Adjust prompt detail and token limits to control response quality and length.

Verified 2026-04 · claude-3-5-sonnet-20241022

Verify ↗