Getting consistent, well-structured responses can be challenging when working with LLMs. Traditional prompting often leads to unpredictable results, making relying on AI assistance for complex tasks difficult.
While exploring prompt engineering techniques this year, I discovered an interesting approach: Tagged Prompts. This method has improved my interactions with AI, delivering more thoughtful responses.
Tagged prompts borrow from XML’s structured approach to data organization. By wrapping different parts of our prompts in descriptive tags, we create a clear framework for AI responses. Think of it as creating a mental model that guides the AI’s thinking process.
I want to learn software engineering. What should I do?
🤖
I'll help you create a structured path to learn software engineering. Here's a comprehensive approach:
First, start with programming fundamentals:
1. Learn a beginner-friendly programming language like Python or JavaScript
2. Master basic concepts like variables, data types, control flow, functions, and object-oriented programming
3. Practice with small projects to reinforce your learning
Once you have the basics, focus on:
- **Version Control**: Learn Git and GitHub to manage code and collaborate with others
- **Data Structures & Algorithms**: Understanding these is crucial for writing efficient code and passing technical interviews
- **Development Tools**: Get comfortable with an IDE (like VS Code), command line, and debugging tools
- **Web Development Fundamentals**: HTML, CSS, and JavaScript if you're interested in web development
- **Testing**: Learn about unit tests, integration tests, and test-driven development
- **Databases**: Start with SQL basics, then learn about database design
Practical steps you can take:
1. Choose learning resources:
- Free platforms like freeCodeCamp, The Odin Project, or CS50x
- Paid platforms like Udemy, Coursera, or boot camps
- Technical books and documentation
2. Build projects:
- Start with small, achievable projects
- Gradually increase complexity
- Create a portfolio to showcase your work
3. Join the community:
- Participate in coding forums like Stack Overflow
- Join local coding meetups
- Contribute to open source projects
Would you like me to suggest some specific resources for any of these areas? Or would you prefer to focus on a particular aspect of software engineering?
Before vs After: Impact of Tagged Prompts on AI Responses#
Step-by-Step Guide to Implementing Tagged Prompts#
Tagged prompts can be implemented in two ways:
As a system prompt for ongoing AI interactions
As part of individual conversation messages
👁 Claude System Prompt Example of how a system prompt with instructions on Claude's project looks like.
Here’s a simple but effective system prompt structure:
System Prompt
When answering queries:
1. Think through your reasoning in <thinking> tags
2. Provide your answer in <output> tags
3. If you spot an error, explain and correct it in <reflection> tags
I want to learn software engineering. What should I do?
🤖
<thinking>
Let me break this down systematically:
1. Software engineering is a broad field - need to cover both fundamentals and practical skills
2. Should suggest a structured learning path that's manageable
3. Important to emphasize both theoretical knowledge and hands-on practice
4. Need to include guidance on building a portfolio and joining the community
5. Should consider both formal and self-learning options
</thinking>
<output>
Here's a comprehensive path to get started with software engineering:
Start with Programming Fundamentals:
Begin with Python or JavaScript - they're beginner-friendly and widely used. Focus on basics like variables, control flow, functions, and data structures. Platforms like freeCodeCamp or The Odin Project offer free structured courses.
Build Computer Science Foundation:
Learn core concepts like:
Data structures (arrays, linked lists, trees)
Basic algorithms and their complexity
How computers work at a basic level
Version control with Git
Practice Project-Based Learning:
Start with small projects that teach fundamentals
Gradually increase complexity as you learn
Build projects that solve real problems you encounter
Document your code and maintain a GitHub portfolio
Join the Community:
Participate in coding communities on Discord or Reddit
Contribute to open source projects
Attend local tech meetups or virtual events
Find a mentor or study group
Recommended Learning Path:
Month 1-2: Programming basics and Git
Month 3-4: Web development fundamentals (HTML, CSS, JavaScript)
Month 5-6: Choose a specialization (backend, frontend, mobile, etc.)
Month 7-8: Build portfolio projects
Month 9+: Advanced topics and job preparation
Resources to Consider:
CS50 from Harvard (free on edX) for computer science basics
freeCodeCamp for web development
"Clean Code" by Robert Martin for best practices
LeetCode for coding practice
Would you like me to elaborate on any of these areas or suggest resources for a specific aspect you're most interested in?
</output>
<reflection>
After reviewing my response, I note that while comprehensive, I could have:
1. Emphasized the importance of learning testing early in the process
2. Mentioned the value of understanding databases
3. Included information about different learning styles and approaches
However, these can be addressed in follow-up discussion based on the human's interests and needs.
</reflection>
For more sophisticated applications, we can add quality metrics and step tracking:
System Prompt
Use <thinking> tags to explore different approaches and viewpoints
Use <step> tags to break down the solution (20 step budget, request more if needed)
Add <count> tags after each step to track remaining budget
Use <reflection> tags to evaluate progress and be self-critical
Rate quality with <reward> tags (0.0-1.0):
- Greater than or equal to 0.8: Continue approach
- Between 0.5 and 0.7: Minor adjustments
- Less than 0.5: Try new approach
Show all work and calculations explicitly
Explore multiple solutions when possible
Summarize final answer in <answer> tags
End with final reflection and reward score
Adjust strategy based on reward scores and intermediate results
Tagged Prompts in Production: v0 by Vercel Case Study#
Vercel’s AI assistant v0 demonstrates how tagged prompts work in production. Their implementation, revealed through a leaked prompt on Reddit, shows the power of structured prompts in professional tools.
Key Takeaways: Getting Started with Tagged Prompts#
This was just a quick overview to explain the basic idea of tagged prompts.
I would suggest trying out this technique for your specific use case.
Compare responses with tags and without tags to see the difference.
Stay Updated!
Subscribe to my newsletter for more TypeScript, Vue, and web dev insights directly in your inbox.
Background information about the articles
Weekly Summary of all the interesting blog posts that I read
