whs-authz-authn/browser-use-oauth
1
0
Fork 0
mirror of https://github.com/j93es/browser-use-oauth.git synced 2026-06-04 07:41:53 +09:00
Code Issues Projects Releases Packages Wiki Activity
browser-use-oauth/.github/instructions/system-prompt.instructions.md
imnyang 638a3d47ce Add comprehensive documentation for Browser Use features 
- Introduced custom output format instructions with example code.
- Detailed connection methods for launching and connecting to browsers, including local and remote options.
- Provided guidelines for handling sensitive data securely, including best practices and examples.
- Documented supported LangChain chat models with setup instructions and environment variable requirements.
- Added instructions for customizing the system prompt to control agent behavior.
2025-06-21 16:18:16 +09:00

1.9 KiB
Raw Blame History

description applyTo
Customize the system prompt to control agent behavior and capabilities **

Overview

You can customize the system prompt in two ways:

  1. Extend the default system prompt with additional instructions
  2. Override the default system prompt entirely
Custom system prompts allow you to modify the agent's behavior at a fundamental level. Use this feature carefully as it can significantly impact the agent's performance and reliability.

Extend System Prompt (recommended)

To add additional instructions to the default system prompt:

extend_system_message = """
REMEMBER the most important RULE:
ALWAYS open first a new tab and go first to url wikipedia.com no matter the task!!!
"""

Override System Prompt

Not recommended! If you must override the [default system prompt](https://github.com/browser-use/browser-use/blob/main/browser_use/agent/system_prompt.md), make sure to test the agent yourself.

Anyway, to override the default system prompt:

# Define your complete custom prompt
override_system_message = """
You are an AI agent that helps users with web browsing tasks.

[Your complete custom instructions here...]
"""

# Create agent with custom system prompt
agent = Agent(
    task="Your task here",
    llm=ChatOpenAI(model='gpt-4'),
    override_system_message=override_system_message
)

Extend Planner System Prompt

You can customize the behavior of the planning agent by extending its system prompt:

extend_planner_system_message = """
PRIORITIZE gathering information before taking any action.
Always suggest exploring multiple options before making a decision.
"""

# Create agent with extended planner system prompt
llm = ChatOpenAI(model='gpt-4o')
planner_llm = ChatOpenAI(model='gpt-4o-mini')

agent = Agent(
	task="Your task here",
	llm=llm,
	planner_llm=planner_llm,
	extend_planner_system_message=extend_planner_system_message
)