Skip to content
Aakash GuptaAakash Gupta

Complete Vibe Coding Tutorial: Build a Full Stack App with AI | Andy Carroll (Windsurf)

What if you could launch a product next week without writing a single line of code? Today, it's possible. Andy Carroll (a 16 year PM and vibe coding expert) shows you exactly how to vibe-code your way into building great products — by building a $1M app live, right in front of you. We're discussing: Preview – 00:00:00 What Is Vibe Coding? – 00:01:57 Vibe Coding Tutorial Begins – 00:05:18 Ad – 00:10:32 Ad – 00:11:20 Building a Full-Stack Mobile App – 00:12:16 Creating the AI Sports Reporter – 00:18:12 Developing AI Tools Live – 00:21:22 Ad – 00:30:33 AI Sports Reporter (Part 2) – 00:31:25 Reviewing the Learning Page – 00:34:18 Using Prompts to Generate a Brand Logo – 00:42:04 Designing an Infographic – 00:46:49 Why Prompt Quality Is Everything – 00:50:21 Recap of the Live Build Session – 00:53:59 How PMs Should Use These Tools – 00:58:34 The Future of Vibe Coding for PMs – 01:00:15 What Is Aisle Partners? – 01:04:08 Should PMs Consult, Stay Full-Time, or Build Their Own Product? – 01:07:24 Closing Notes – 01:11:20 Podcast transcript + infographic: https://www.news.aakashg.com/p/andy-carroll-podcast 💼 Check out our sponsors: Maven: I’ve just launched my unique curation of their top courses - http://maven.com/x/aakash Miro: The innovation workspace: your team’s canvas - http://miro.pxf.io/PO4WZX Amplitude: Try their 2-min assessment of your company’s digital maturity - https://bit.ly/4hl25RG 👀 Where to find Andy LinkedIn: https://www.linkedin.com/in/heyandycarroll Aisle Partners: https://www.aisle.partners 👨‍💻 Where to find Aakash: Twitter: https://www.twitter.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aagupta/ Instagram: https://www.instagram.com/aakashg0/ 🔑 Key Takeaways 1. Vibe coding puts product creation in non-technical hands. Even after 15 years as a PM, Andy can't write code from scratch. But AI tools like Windsurf and Lovable made it possible for him to collaborate with AI to build real products without coding skills. 2. Front-load your planning to avoid rebuilding everything. He painfully learned that diving straight into coding creates expensive headaches. So, it’s best to use AI to draft strategy documents and architecture plans first, preventing the frustration of multiple false starts. 3. Set up a simple deployment pipeline immediately. GitHub for code, Netlify for deployment, and Superbase for databases is his recommended stack. Deploy frequently and early as waiting too long means facing hundreds of errors at once instead of fixing small issues. 4. Create PM deliverables in hours, not weeks. He built a detailed product roadmap and strategy documents in a single afternoon. These become living references in GitHub that team members can access anytime, eliminating version control nightmares. 5. Watch out for AI's eagerness to change your code. Windsurf has two modes: safe "chat" and powerful "write." Only toggle to write mode when you want changes made, otherwise, AI might drastically refactor your entire page when you just want a font color change. 6. Switch AI models when you hit roadblocks. Different models have different strengths. He uses Claude 3.7 for brainstorming, DeepSeek for specific tasks, and switches to GPT-4 when stuck. A fresh model may solve problems that the first one couldn't. 7. Validate ideas faster than ever before. Skip weeks of perfecting logos, brands, and pixel-perfect designs. Build something "good enough" quickly, get real feedback, and iterate based on actual user responses rather than internal debates. 8. Target your creativity where it matters most. AI tools eliminate 90% of implementation busy work. Use templates for standard elements like landing pages, then focus your team's energy exclusively on the features that truly differentiate your product. 9. Automate status reports and presentations. He generates comprehensive project updates directly from his roadmap progress, feeding them into presentation tools like Gamma. This eliminates hours spent creating the same PowerPoint slides teams have made for decades. 10. People are launching profitable side hustles with vibe coding. Entrepreneurs like Peter Levels and John Rush build and monetize micro-SaaS products through vibe coding. The approach allows testing ideas quickly and pivoting without emotion when something doesn't work. #AI #startup #vibecoding 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 170K listeners. Hosted by Aakash Gupta, who spent 16 years in PM, rising to VP of product, this 2x/ week show covers product and growth topics in depth. 🔔 Subscribe and like the video to support our content! And turn on the bell for notifications.

Aakash GuptahostAndy Carrollguest
May 16, 20251h 12mWatch on YouTube ↗

CHAPTERS

  1. Defining “vibe coding”: humans + AI building together

    Aakash and Andy open by clarifying what “vibe coding” actually means: using AI development tools as a creative partner to rapidly bring products to life. They also highlight an important product lesson—start by defining what makes the idea unique and focus energy there.

  2. Choosing a tool: why Andy prefers Windsurf (vs. v0, Lovable, Replit, Cursor)

    Andy compares popular AI dev tools and explains where each fits in a builder’s journey. He positions Windsurf as a more powerful, full-stack-friendly editor with broad model access, after hitting limits with simpler “quick-start” tools.

  3. First look at Windsurf’s workspace: projects, files, and Cascade

    Andy screen-shares and demystifies Windsurf’s UI: a file tree on the left, code in the middle, and the Cascade chat panel on the right. He emphasizes that it can look intimidating at first, but is essentially folders + an AI editor.

  4. Cascade modes that matter: Chat vs. Write (and why it can break things)

    Andy explains the crucial difference between Chat mode (safe, no edits) and Write mode (AI can directly change code). He warns that AI can be overzealous—small requests can trigger large refactors—so controlling permissions is essential.

  5. Model selection strategy: using different LLMs for different tasks

    They discuss how different models perform better depending on the job—broad thinking vs. tactical debugging. Andy shares a practical workflow: switch models when stuck, and leverage “thinking” variants to explore tradeoffs and context.

  6. Planning before building: prompt libraries, product docs, and avoiding false starts

    Andy describes an early mistake: jumping straight into building without enough planning led to expensive rework. He now uses a structured prompt library and lightweight product artifacts (strategy, architecture, roadmap) to clarify direction before coding.

  7. Project case study: the AI sports match reporter idea and early prototype

    Andy shares the origin story: a kids’ football match report sparked an idea for an AI match reporter that generates written and audio outputs. He shows how he’s iterating from a simple waitlist/landing page toward a fuller multi-app product.

  8. From PM artifacts to a single cockpit: roadmap + GitHub as the shared source of truth

    Andy shows how he stores strategy docs, prompts, and roadmaps inside the repo so the whole project context lives alongside the code. He highlights how this makes status reporting and alignment dramatically faster for teams and stakeholders.

  9. Deployment lessons: why “deploy early” matters (Netlify/Vercel)

    Andy contrasts one-click deployments in simpler tools with the more complex reality of full-stack setups. His key lesson: deploy the simplest working version early and often to avoid painful late-stage deployment failures.

  10. Live edit demo: fixing landing page contrast with screenshot + Write mode

    They perform a real-time improvement: Andy uses a screenshot, prompts the model, and updates the “Coming Soon” text color for readability. This segment reinforces how quickly AI can turn UI feedback into code changes and deployments.

  11. Local dev vs. production: running localhost and using the terminal inside the IDE

    Andy demonstrates spinning up the site locally (localhost) and notes how Windsurf reduces tool-switching by integrating terminal commands. They compare seeing changes immediately locally vs. waiting for production deploys.

  12. Shipping more features live: logo + favicon + “How it works” infographic section

    They generate a basic brand logo and favicon via a prompt, then implement them directly into the site. Next, they add an interactive “How it works” section, showing how AI can quickly create polished, hoverable UI components from a simple prompt.

  13. Big-picture takeaways: creativity, team alignment, and monetization paths

    Andy argues AI dev tools increase creativity by collapsing the cost of experimentation and feedback. They discuss monetization via micro-SaaS, rapid trials (Peter Levels), and consulting/enablement as another pathway.

  14. Implications for PMs and Andy’s career journey: from 2008 to AI-driven building

    They reflect on how product management has evolved and why this shift feels bigger than prior movements like Agile. Andy shares his path from finance to product, his current work at Aisle Partners (training + implementation), and the realities of going independent.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome