---
description: 
globs: 
alwaysApply: false
---
---
description: "AI prompting best practices and LLM interaction patterns. Includes prompt engineering, context management, and agent design principles."
globs: "*.py,*.ts,*.js,*prompt*,*ai*,*llm*"
alwaysApply: false
---

# AI Prompting & LLM Best Practices

Elite prompting techniques for Gauntlet AI graduates.

## Prompt Engineering Principles

### Structure Your Prompts
- Use clear, specific instructions
- Provide context and examples
- Break complex tasks into steps
- Define output format expectations

### Context Management
```python
# Good: Structured context
system_prompt = """
You are a senior software engineer reviewing code.
Focus on: security, performance, maintainability.
Provide specific, actionable feedback.
"""

user_prompt = f"""
Review this function:
{code_snippet}

Check for potential issues and suggest improvements.
"""
```

### Temperature Guidelines
- **0.1-0.3**: Code generation, factual responses
- **0.4-0.7**: Creative writing, brainstorming
- **0.8-1.0**: Highly creative tasks

## Agent Design Patterns

### Tool Usage
- Define clear tool interfaces
- Handle errors gracefully
- Implement retry logic
- Log all interactions

### Multi-Agent Systems
- Clear role definitions
- Handoff protocols
- State management
- Communication patterns

*This is a placeholder rule. Contribute advanced AI patterns to expand this rule.*