Update prompting/prompt-engineering-guide.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

Author: Gerome-Elassaad

prompting/prompt-engineering-guide.mdx

@@ -53,64 +53,62 @@ Build an online store dashboard with:
 - Mention if you need user login
 - Tell it how to check if data is correct
 
-## Advanced AI prompting techniques for code generation
+## How to Ask Better Questions
 
-### Contextual information for better LLM results
+### Give the AI Context
 
-**Provide relevant context for AI code generation:**
+**Help the AI understand your situation:**
 
-- Include existing code snippets when relevant for AI understanding
-- Reference specific files or components for LLM context
-- Mention current technology constraints for AI-powered development
-- Specify performance requirements for optimized code generation
+- Show it code you already have
+- Tell it which files you're working on
+- Mention any limits (like "needs to work on old phones")
+- Say if speed is important
 
-**Progressive refinement with AI prompting:**
+**Start Simple, Then Add Details:**
 
-- Start with high-level requirements for AI planning
-- Add implementation details iteratively for better LLM results
-- Use follow-up prompts for AI clarification
-- Build upon previous AI responses for iterative development
+- First, explain what you want in general
+- Then add more specific details
+- Ask follow-up questions if needed
+- Build on what the AI already created
 
-### LLM-specific optimization for AI coding
+### Tips for Different AI Models
 
-**Claude/Gemini AI models:**
+**For Claude or Gemini:**
 
-- Provide comprehensive context upfront for better AI code generation
-- Use structured formats (numbered lists, sections) for LLM understanding
-- Include examples and edge cases for robust AI development
-- Specify output format preferences for consistent code generation
+- Give all the information at once
+- Use numbered lists to organize your thoughts
+- Include examples of what you want
+- Say how you want the answer formatted
 
-**GPT AI models:**
+**For GPT:**
 
-- Break complex requests into smaller parts for better LLM processing
-- Use clear, direct language for optimal AI code generation
-- Provide concrete examples for accurate LLM understanding
-- Specify desired output structure for consistent AI results
+- Break big requests into smaller pieces
+- Use simple, clear language
+- Show examples of what you mean
+- Be specific about what you want
 
-### Error Prevention
+### Avoid Common Mistakes
 
-**Common Pitfalls to Avoid:**
+**Don't do this:**
 
-- Vague requirements that lead to assumptions
-- Missing technical specifications
-- Inconsistent naming conventions
-- Unspecified integration requirements
+- Be too vague ("make it better")
+- Forget to mention important details
+- Use different names for the same thing
+- Forget to say how things should connect
 
-**Validation Techniques:**
+**Do this instead:**
 
-- Include acceptance criteria
-- Specify testing requirements
-- Define success metrics
-- Request validation checkpoints
+- Include clear goals ("make the button blue and centered")
+- Specify what success looks like
+- Say how you'll test it
+- Ask for checkpoints along the way
 
 <Callout type="info">
-  **Version Specification**: When possible, specify framework versions to ensure compatibility and avoid deprecated
-  features.
+  **Version Numbers**: If you know which version of a tool you're using, tell the AI. This helps it give you code that works.
 </Callout>
 
 <Callout type="tip">
-  **Iterative Refinement**: Start with a clear prompt, then use follow-up messages to add details and make adjustments
-  as needed.
+  **Start Simple**: Begin with a clear request, then add more details in follow-up messages.
 </Callout>
 
 ## AI prompt engineering best practices summary