Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Understanding Vibe Coding: How to Leverage Nont...

Avatar for Emery Fertic Emery Fertic
June 10, 2026
19

Understanding Vibe Coding: How to Leverage Nontechnical Expertise

Avatar for Emery Fertic

Emery Fertic

June 10, 2026

More Decks by Emery Fertic

Transcript

  1. Understanding Vibe Coding: how to leverage nontechnical expertise Coco Zhang

    • 6 May 2026 Supervisor: Melissa Webster, Senior Lecturer, MIT Sloan
  2. AGENDA 3 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implication & Open Questions ➢ Conclusion ➢ Acknowledgement & Resources
  3. “There’s a new type of coding I call “vibe coding”,

    where you fully give in to the vibes, embrace exponentials, and forget that code even exists.” — Andrej Karpathy Former OpenAI Founder and Tesla AI Leader, Founder of Eureka Lab
  4. 6 Vibe Coding Challenges the Technical Knowledge Required for Traditional

    Coding Fig 1, 2: X Posts by Andrej Karpathy, 2023/1/24 & 2025/2/2 User Interest Natural Language Code Generation Working Software Enabled through visual interfaces, e.g. Claude, Lovable
  5. “I ask for the dumbest things like “decrease the padding

    on the sidebar by half” because I’m too lazy to find it. I “Accept All” always, I don’t read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it… Sometimes the LLMs can’t fix a bug so I just work around it or ask for random changes until it goes away.” — Andrej Karpathy Former OpenAI Founder and Tesla AI Leader, Founder of Eureka Lab
  6. 8 Vibe Coding Challenges the Technical Knowledge Required for Traditional

    Coding Specification Implementation Debugging Traditional Coding Workflow: Code Generation Inspection Regeneration and Iteration Vibe Coding Workflow: ** done through natural language ** done through code
  7. 9 Vibe Coding as a Technological and Cultural Change Blooming

    Generative AI Tools: New builders and developers Popular opinions at the Frontier of Tech
  8. AGENDA 10 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implication & Open Questions ➢ Conclusion ➢ Acknowledgement & Resources
  9. AGENDA 12 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implication & Open Questions ➢ Conclusion ➢ Acknowledgement & Resources
  10. 13 Primary Research: Four-month-long work by the UROP team using

    different tools to vibe code apps - 20+ Use Cases Collected - 4 Platforms Used Secondary Research with Literature Review: Read blogs and papers analyse popular case studies and workflows in vibe coding communities GenAI Assistance in Research • Critique and tighten my research question • Assisting with qualitative data analysis
  11. 14 Defining the Nontechnical Vibe Coder Minimal Coding Mental Model

    • Does not know web/software development • Avoids file structures and manual debugging • Relies on conversational iteration Individual Creative Workflow • Works independently • No interest in GitHub collaboration workflows • Treats software like a personal creative medium Low-Stake Small- Scale Projects • Small-scale or disposable projects • Operates within token limits • Minimal concern for security complexity
  12. 15 Vibe coding Platforms and Evaluation Framework in Primary Research

    Quantitative Evaluation Metrics: Effort invested Ease of use Smoothness of iteration Qualitative Data: Prompt Design Debugging Strategies Comparative analysis across different vibe coding platforms.
  13. 16 Use Cases Across Categories of Application Technical MechE Experiments

    Simulation Productivity Meeting to Decision Transcript Summary Lifestyle Protein Intake Tracker Creative Music Visualisation Mapping the types of projects we explored through conversational software creation
  14. AGENDA 17 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implication & Open Questions ➢ Conclusion ➢ Acknowledgement & Resources
  15. 18 Ideation What project do we want to vibe code?

    What problem are we trying to solve? Creation How do we build effectively through Prompting? Improvement How do we identify meaningful improvements? How do we solve it through prompting? , , , Adoption Do we continue using this project? Vibe Coding can be divided into four stages.
  16. 19 Ideation What project do we want to vibe code?

    What problem are we trying to solve? Creation How do we build effectively through Prompting? Improvement How do we identify meaningful improvements? How do we solve it through prompting? , , , Adoption Do we continue using this project?
  17. 20 Ideas are Hard to Come By, But We Found

    Three Patterns of Vibecoding Ideation We found inspiration from online blogs. We want apps to fit our habits. We want to test the technical boundaries of Vibe Coding. Deeksha’s Polaroid App Coco’s Dictionary App Melissa’s Protein Intake Tracker App Deeksha’s Outreach Personalizer App Emery’s Oura Ring Biking Tracker App Coco’s Doom Scrolling Intervention App Replication Personalization Technical Exploration
  18. 21 Tool Differences Narrowed as Prompting Skills Improved Lovable and

    Replit appear strongest overall. Claude has the most use cases due to familiarity with the platform. Effort scores for individual projects become increasingly less correlated to performance ratings. The various patterns show a large spread within a single platform. Performance depended heavily on the specific project context.” Fig 1: Comparison between our average evaluation scores on Lovable, Replit, Google AI Studio, Claude, and Base 44
  19. 22 Technical Integrations Reveal Platform Differences Fig 1: Deeksha’s Use

    Case Travel Planner on Claude and Lovable Low Technical Complexity → Similar Performance Fig 2: Emery’s Use Case Oura Ring Bike Tracker on Claude, Replit, and Lovable API Integration → Diverging Performance
  20. 23 Ideation What project do we want to vibe code?

    What problem are we trying to solve? Creation How do we build effectively through Prompting? Improvement How do we identify meaningful improvements? How do we solve it through prompting? , , , Adoption Do we continue using this project?
  21. 24 Meta-Prompting is the Most Effective Prompting Strategy Generating Better

    Prompts Before Generating Code • Initial App Design • Structured Specification • Code Architecture How to Adopt in Vibe Coding? Instead of asking AI directly for an output, you ask AI to first design the reasoning structure for the task. What is Meta Prompting?
  22. 25 Metaprompting is the Most Effective Prompting Strategy Generating Better

    Prompts Before Generating Code • Initial App Design • Structured Specification • Code Architecture How to Adopt Metaprompting in Vibe Coding? Instead of asking AI directly for an output, you ask AI to first design the reasoning structure for the task. What is Meta Prompting? User LLM Vibe Coding Tool Product Take an Extra Step Here!
  23. 26 Metaprompting Adds the Most Value When Translating Ambiguity to

    Structure Costly Metaprompting Solving already localised, specific problems High-Leverage Metaprompting Formalising ideas and inspirations into effective frameworks Structuring Ambiguous Ideas Translating Creative Ideas into Implementable Features Planning Systems Architecture Before Generation
  24. 27 Metaprompting Adds the Most Value When Translating Ambiguity to

    Structure Structuring Ambiguous Ideas Translating Creative Ideas into Implementable Features Planning Systems Architecture Before Generation “I want to make a website that updates me on local screenings and concerts.” Initial Idea: Metaprompting: Break down with: • UI style • user workflow • data sources • APIs • architecture • scope boundaries
  25. 28 How to Use Meta Prompting to Generate Initial Prompts:

    Poem Website Use Case “I have a poem I want to present in dynamic and interactive website. give me different ideas for my website based on the content of the poem, you need to include every line and the title of the poem but have creative freedom in your design. I would like you to develop prompts that I can give to vibecoding tools for building the website:” Fig 1: One of the prompts generated by ChatGPT 5.5 Instant (New Model Released) The prompt details technical and design requirements according to my initial prompt. • Design Requirement • Interaction • Style • Output
  26. 29 Metaprompting Adds the Most Value When Translating Ambiguity to

    Structure Structuring Ambiguous Ideas Translating Creative Ideas into Implementable Features Planning Systems Architecture Before Generation “I want the website to feel more interactive.” Initial Idea: Metaprompting: ”Sections should animate sequentially on scroll, with toggleable visual elements and hover feedback.”
  27. 30 Metaprompting Adds the Most Value When Translating Ambiguity to

    Structure Structuring Ambiguous Ideas Translating Creative Ideas into Implementable Features Planning Systems Architecture Before Generation “Help me design the architecture for a personal finance dashboard before generating code.” Prompt Input: Metaprompting: Define: • page hierarchy • component structure • state management • data flow • file organization
  28. 31 Ideation What project do we want to vibe code?

    What problem are we trying to solve? Creation How do we build effectively through Prompting? Improvement How do we identify meaningful improvements? How do we solve it through prompting? , , , Adoption Do we continue using this project?
  29. “Expertise clearly still matters in a world of creating things

    with words. After all, you have to know what you want to create; be able to judge whether the results are good or bad; and give appropriate feedback. This underscores how vibe coding isn't about eliminating expertise but redistributing it— from writing every line of code to knowing enough about systems to guide, troubleshoot, and evaluate.” — Ethan Mollick Wharton Professor
  30. 33 Non-technical Users Can Do Debugging with Limitations Identify Issues

    with the Product, Especially Testing the Edge Cases If you’re creating a Polaroid filter app, can it take HEIC files? (photos took on iPhones) Restart or Switch Tools Restarting a project only requires a new prompt with vibe coding and can bring about fresh results. Technical insights might be helpful to identify the causes of these bugs. Include Command in Prompts “Debug as you go along” Debugging with Positive or Negative Examples “Create a community feature on my food rating app like Beli” The minimum viable knowledge for effective debugging: your understanding of your needs and the tool you’re using.
  31. 34 Ideation What project do we want to vibe code?

    What problem are we trying to solve? Creation How do we build effectively through Prompting? Improvement How do we identify meaningful improvements? How do we solve it through prompting? , , , Adoption Do we continue using this project?
  32. 35 Adoption is Difficult Because It Involves Habit Change. Behavioural

    Friction Users already have entrenched digital habits Technological Friction Vibe-coded tools often lack mobile-native convenience and ecosystem integration
  33. AGENDA 36 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implications & Open Questions ➢ Conclusion ➢ Acknowledgement & Resources
  34. 37 Implications for Nontechnical Users Need Identification Identifying and understanding

    problems became an important nontechnical skill. Creative Integration between Tech and Personal Life / Hobbies We can all be micro-entrepreneurs. Adoption might take off more with mobile integration. Vibe coding converges with our day-to-day habits. Flatter Learning Curve Software development usually requires a steep learning curve. Build Custom Tools for ourselves
  35. How much can users build without understanding the systems underneath?

    How do we make vibe coding reliable for nontechnical creators? 38 Open Questions
  36. AGENDA 39 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implication & Future Directions ➢ Conclusion ➢ Acknowledgement & Resources
  37. 40 Ideas are hard to come by, but we found

    three patterns of vibecoding ideation. Tool differences narrowed as prompting skills improved Creation: Meta-prompting is the most effective prompting strategy. Adoption is difficult because it involves habit change. Improvement: Nontechnical users can do debugging with limitations.
  38. AGENDA 41 ➢ Context ➢ Research Question ➢ Methodology ➢

    Key Findings ➢ Implication & Future Directions ➢ Conclusion ➢ Acknowledgement & Resources
  39. 42 Acknowledgements • My advisor, Melissa • My teammates, Deeksha,

    Emery, and Nadine Resources Individuals Blogs: • Andrej Karpathy’s Tweets. • Simon Wilison’s Web Blog. URL: https://simonwillison.net/ • Zara Zhang’s Blogs. URL: https://zarazhang.com/writing-profiles/ Forums and Discussions • Claude Artifacts for providing inspiration and tools for vibe coding. URL: https://madewithclaude.com/
  40. Understanding Vibe Coding: how to leverage nontechnical expertise Coco Zhang

    • 6 May 2026 Supervisor: Melissa Webster, Senior Lecturer, MIT Sloan