Lesson 3

Prompt Structure

Order matters

The Problem: You write prompts that seem clear to you, but AI gives unexpected results. Is there a better way to structure prompts for consistency?

The Solution: Anatomy of a Good Letter

Prompt structure is about organizing the components of your prompt in a clear, logical way. It's like writing a good business letter — header, context, request, closing — each part serves a purpose. The structure typically starts with a system prompt, and can include few-shot examples to guide the model.

Think of it like a well-structured letter:

1. Context/Background: What situation is the AI responding to?
2. Instruction/Task: What exactly should the AI do?
3. Input Data: What material should it work with?
4. Output Format: How should the response be structured?

Common Structure Patterns

Delimiters: Use ### or XML tags to separate sections
Placeholders: Mark variable content with brackets
Order matters: Instructions at start/end get more attention
Be explicit: Don't assume AI understands implicit context

Fun Fact: Studies show that using XML-style tags (like <context> and <instruction>) can improve task completion by 10-15% compared to plain text because it helps the model parse the prompt structure!

Try It Yourself!

Use the interactive example below to experiment with different prompt structures and see how organization affects AI outputs.

Prompt Structure — Order Matters!

🔀 Drag blocks to change prompt order. Models pay more attention to the beginning and end!

Prompt structure:

📋
Context
You are a Python programming assistant
#1
🎯
Task
Write an array sorting function
#2
📝
Output format
Return only code without explanations
#3
💡
Examples
Example: [3,1,2] → [1,2,3]
#4
⚠️
Constraints
Don't use built-in sort()
#5

Final prompt:

You are a Python programming assistant

Write an array sorting function

Return only code without explanations

Example: [3,1,2] → [1,2,3]

Don't use built-in sort()

Model attention (approximate):

StartMiddleEnd

✓ Good practices

• Context and role — at the start
• Main task — right after context
• Output format — closer to the end

✗ Avoid

• Task at the very end
• Constraints at the start
• Examples without context

Key Insight

Transformers pay more attention to the start and end of context ("Lost in the Middle" effect). Place important information in these positions for better results.

Optimal Prompt Structure:

📝Template 1: Basic Structure

# Role
You are a web development expert

# Context
I have a React project with TypeScript

# Task
Create a reusable component to display a product list

# Output format
Return ready-to-use code with TypeScript types and comments

# Constraints
Don't use third-party libraries, only React

🎯Template 2: For Complex Tasks

# Role and Expertise
You are an experienced Senior Backend Developer. Your expertise: microservices architecture, database optimization, API design.

# Task Context
User: Startup with growing API load
Goal: Optimize performance and reduce latency
Constraints: Infrastructure budget is limited

# Input Data
Current architecture: Node.js monolith + PostgreSQL
Load: 1000 requests/sec during peak hours
Average response latency: 300ms

# Instructions
1. First analyze current bottlenecks
2. Then propose specific optimization solutions
3. Finally estimate approximate costs and implementation timeline

# Response Format
Answer in the format:
- Analysis: [identified issues]
- Recommendations: [top 3 solutions with priorities]
- Next steps: [2-week action plan]

# Examples (few-shot)
Input: "API responds slowly under high load"
Output: "Analysis: Main issue is lack of caching and N+1 database queries. Recommendations: 1) Implement Redis for caching popular requests 2) Optimize SQL queries using JOIN 3) Add pagination for large lists..."

🔢Element Ordering Rule

# Prompt Element Ordering Rule:

1. System instructions (at the beginning)
   → Role, expertise, communication style

2. Context and examples (in the middle)
   → Background information, few-shot examples

3. User question (at the end!)
   → Specific task — closer to model output

Why? Models better account for information from the start and end of context ("Lost in the Middle" effect).

💡 How to Use Templates

• Choose the appropriate template based on task complexity
• Replace examples in [...] with your data
• For simple questions, the basic template is sufficient
• For expert tasks, use the complex template with few-shot examples
• Remember: user question always at the end!

Try it yourself

Interactive demo of this technique

Technique Comparison

Demo Mode

Pre-recorded responses

TaskBeginnerWriting

Structuring a prompt — flat text vs. clear markup with delimiters

Without technique

Prompt

Write a product description for an online store. Product: wireless headphones. Price $79.99. Bluetooth 5.3, noise cancellation, 30 hours battery. For the product page need: title, 3 bullet points of benefits, short description under 100 words. Friendly tone.

Response

Wireless headphones — great choice! With Bluetooth 5.3 and noise cancellation they are perfect for music, work, and travel. 30 hours battery life. Price: $79.99.

Tokens:55/38

Time:250ms

Quality:

With Context Structure

With technique

Prompt

<role>You are a copywriter for an electronics online store</role> <product> Name: SoundWave Pro Type: wireless headphones Price: $79.99 Specs: Bluetooth 5.3, active noise cancellation, 30h battery </product> <format> 1. Title (up to 10 words, with emotion) 2. 3 benefit bullet points (each up to 15 words) 3. Description (up to 100 words, friendly tone) </format> <constraints> - Do not mention competitors - Include price in description </constraints>

Response

Dive into Sound — SoundWave Pro Changes the Game

Active noise cancellation: your music, nothing else
30 hours without charging: enough for a whole week of commutes
Bluetooth 5.3: instant connection to any device

SoundWave Pro is made for those who value quality and freedom. Enjoy your favorite tracks in crystal-clear sound while noise cancellation blocks out the world. 30 hours of battery means you can forget about charging for days. All this for just $79.99.

👁️XML tags separate role, data, format, and constraints — the model does not get confused

🧠Flat text mixes everything together — the model loses the response structure

✅Structured prompt = predictable and controllable output

Tokens:95/110

Time:420ms

Quality:

Why this works

XML tags and clear sections in the prompt are like markup for the model. It knows exactly where the data, format, and constraints are.

1 / 2

Practice Challenges

Create a free account to solve challenges

3 AI-verified challenges for this lesson

Related lessons:Prompt Elements System Prompts

This lesson is part of a structured LLM course.

My Learning Path

Lesson 3

Prompt Structure

Order matters

The Problem: You write prompts that seem clear to you, but AI gives unexpected results. Is there a better way to structure prompts for consistency?

The Solution: Anatomy of a Good Letter

Think of it like a well-structured letter:

1. Context/Background: What situation is the AI responding to?
2. Instruction/Task: What exactly should the AI do?
3. Input Data: What material should it work with?
4. Output Format: How should the response be structured?

Common Structure Patterns

Delimiters: Use ### or XML tags to separate sections
Placeholders: Mark variable content with brackets
Order matters: Instructions at start/end get more attention
Be explicit: Don't assume AI understands implicit context

Try It Yourself!

Use the interactive example below to experiment with different prompt structures and see how organization affects AI outputs.

Prompt Structure — Order Matters!

🔀 Drag blocks to change prompt order. Models pay more attention to the beginning and end!

Prompt structure:

📋
Context
You are a Python programming assistant
#1
🎯
Task
Write an array sorting function
#2
📝
Output format
Return only code without explanations
#3
💡
Examples
Example: [3,1,2] → [1,2,3]
#4
⚠️
Constraints
Don't use built-in sort()
#5

Final prompt:

You are a Python programming assistant

Write an array sorting function

Return only code without explanations

Example: [3,1,2] → [1,2,3]

Don't use built-in sort()

Model attention (approximate):

StartMiddleEnd

✓ Good practices

• Context and role — at the start
• Main task — right after context
• Output format — closer to the end

✗ Avoid

• Task at the very end
• Constraints at the start
• Examples without context

Key Insight

Transformers pay more attention to the start and end of context ("Lost in the Middle" effect). Place important information in these positions for better results.

Optimal Prompt Structure:

📝Template 1: Basic Structure

# Role
You are a web development expert

# Context
I have a React project with TypeScript

# Task
Create a reusable component to display a product list

# Output format
Return ready-to-use code with TypeScript types and comments

# Constraints
Don't use third-party libraries, only React

🎯Template 2: For Complex Tasks

# Role and Expertise
You are an experienced Senior Backend Developer. Your expertise: microservices architecture, database optimization, API design.

# Task Context
User: Startup with growing API load
Goal: Optimize performance and reduce latency
Constraints: Infrastructure budget is limited

# Input Data
Current architecture: Node.js monolith + PostgreSQL
Load: 1000 requests/sec during peak hours
Average response latency: 300ms

# Instructions
1. First analyze current bottlenecks
2. Then propose specific optimization solutions
3. Finally estimate approximate costs and implementation timeline

# Response Format
Answer in the format:
- Analysis: [identified issues]
- Recommendations: [top 3 solutions with priorities]
- Next steps: [2-week action plan]

# Examples (few-shot)
Input: "API responds slowly under high load"
Output: "Analysis: Main issue is lack of caching and N+1 database queries. Recommendations: 1) Implement Redis for caching popular requests 2) Optimize SQL queries using JOIN 3) Add pagination for large lists..."

🔢Element Ordering Rule

# Prompt Element Ordering Rule:

1. System instructions (at the beginning)
   → Role, expertise, communication style

2. Context and examples (in the middle)
   → Background information, few-shot examples

3. User question (at the end!)
   → Specific task — closer to model output

Why? Models better account for information from the start and end of context ("Lost in the Middle" effect).

💡 How to Use Templates

• Choose the appropriate template based on task complexity
• Replace examples in [...] with your data
• For simple questions, the basic template is sufficient
• For expert tasks, use the complex template with few-shot examples
• Remember: user question always at the end!

Try it yourself

Interactive demo of this technique

Technique Comparison

Demo Mode

Pre-recorded responses

TaskBeginnerWriting

Structuring a prompt — flat text vs. clear markup with delimiters

Without technique

Prompt

Response

Wireless headphones — great choice! With Bluetooth 5.3 and noise cancellation they are perfect for music, work, and travel. 30 hours battery life. Price: $79.99.

Tokens:55/38

Time:250ms

Quality:

With Context Structure

With technique

Prompt

Response

Dive into Sound — SoundWave Pro Changes the Game

Active noise cancellation: your music, nothing else
30 hours without charging: enough for a whole week of commutes
Bluetooth 5.3: instant connection to any device

👁️XML tags separate role, data, format, and constraints — the model does not get confused

🧠Flat text mixes everything together — the model loses the response structure

✅Structured prompt = predictable and controllable output

Tokens:95/110

Time:420ms

Quality:

Why this works

XML tags and clear sections in the prompt are like markup for the model. It knows exactly where the data, format, and constraints are.

1 / 2

Practice Challenges

Create a free account to solve challenges

3 AI-verified challenges for this lesson

Related lessons:Prompt Elements System Prompts

This lesson is part of a structured LLM course.

My Learning Path