AI Prompting Cheat Sheet

The Ultimate Prompt Templating Cheat Sheet

From {BASIC} to {{ADVANCED}} in 3 Languages

1

JavaScript/Node.js

2

Python

3

JSON

1

JavaScript Templates

const template = `
You are a {ROLE} specializing in {DOMAIN}.

Task: {TASK}
Output: {FORMAT}
`;

function fillTemplate(template, vars) {
    let result = template;
    for (const [key, value] of Object.entries(vars)) {
        result = result.replace(
            new RegExp(`{${key}}`, 'g'), 
            value
        );
    }
    return result;
}

Best for: Web applications, Node.js backends, real-time template generation

2

Python Templates

class PromptTemplate:
    def __init__(self, template):
        self.template = template
    
    def render(self, **kwargs):
        result = self.template
        for key, value in kwargs.items():
            result = result.replace(
                f"{{{{key}}}}", 
                str(value)
            )
        return result

# Usage
template = PromptTemplate("""
Analyze {{DATA_TYPE}} for {{PURPOSE}}
Input: {{INPUT}}
""")

Best for: Data science, AI/ML pipelines, batch processing, research scripts

3

JSON Configuration

{
  "templates": {
    "analysis": {
      "prompt": "You are a {EXPERT_TYPE}...",
      "variables": ["EXPERT_TYPE", "DATA", "FOCUS"],
      "defaults": {
        "EXPERT_TYPE": "data analyst",
        "FOCUS": "trends and insights"
      }
    }
  },
  "presets": {
    "financial": {
      "EXPERT_TYPE": "financial analyst",
      "DATA_TYPE": "quarterly reports"
    }
  }
}

Best for: Configuration management, API definitions, template libraries

🚀 Quick Reference Guide

Single Braces:
{VARIABLE}
Simple replacement, Python .format() style
Double Braces:
{{VARIABLE}}
Mustache/Handlebars style, advanced templating
Security:
Always sanitize inputs, validate required variables, limit length
Best Practices:
Clear naming, default values, error handling, documentation
Use Cases:
AI prompts, email templates, code generation, dynamic content
Pro Tip:
Build template libraries for reusable, maintainable prompt systems