AI Assisted Coding: From Designer to Solo Developer - Building Production Apps with AI With Elina Patjas

AI Assisted Coding: From Designer to Solo Developer - Building Production Apps with AI In this special episode, Elina Patjas shares her remarkable journey from designer to solo developer, building LexieLearn—an AI-powered study tool with 1,500+ users and paying customers—entirely through AI-assisted coding. She reveals the practical workflow, anti-patterns to avoid, and why the future of software might not need permanent apps at all. The Two-Week Transformation: From Idea to App Store "I did that, and I launched it to App Store, and I was like, okay, so… If I can do THIS! So, what else can I do? And this all happened within 2 weeks." Elina's transformation happened fast. As a designer frustrated with traditional software development where maybe 10% of your original vision gets executed, she discovered Cursor and everything changed. Within two weeks, she went from her first AI-assisted experiment to launching a complete app in the App Store. The moment that shifted everything was realizing that AI had fundamentally changed the paradigm from "writing code" to "building the product." This wasn't about learning to code—it was about finally being able to execute her vision 100% the way she wanted it, with immediate feedback through testing. Building LexieLearn: Solving Real Problems for Real Users "I got this request from a girl who was studying, and she said she would really appreciate to be able to iterate the study set... and I thought: "That's a brilliant idea! And I can execute that!" And the next morning, it was 9.15, I sent her a screen capture." Lexie emerged from Elina's frustration with ineffective study routines and gamified edtech that didn't actually help kids learn. She built an AI-powered study tool for kids aged 10-15 that turns handwritten notes into adaptive quizzes revealing knowledge gaps—private, ad-free, and subscription-based. What makes Lexie remarkable isn't just the technology, but the speed of iteration. When a user requested a feature, Elina designed and implemented it overnight, sending a screen capture by 9:15 AM the next morning. This kind of responsiveness—from customer feedback to working feature in hours—represents a fundamental shift in how software can be built. Today, Lexie has over 1,500 users with paying customers, proving that AI-assisted development isn't just for prototypes anymore. The Workflow: It's Not Just "Vibing" "I spend 30 minutes designing the whole workflow inside my head... all the UX interactions, the data flow, and the overall architectural decisions... so I spent a lot of time writing a really, really good spec. And then I gave that to Claude Code." Elina has mixed feelings about the term "vibecoding" because it suggests carelessness. Her actual workflow is highly disciplined. She spends significant time designing the complete workflow mentally—all UX interactions, data flow, and architectural decisions—then writes detailed specifications. She often collaborates with Claude to write these specs, treating the AI as a thinking partner. Once the spec is clear, she gives it to Claude Code and enters a dialogue mode: splitting work into smaller tasks, maintaining constant checkpoints, and validating every suggestion. She reads all the code Claude generates (32,000 lines client-side, 8,000 server-side) but doesn't write code herself anymore. This isn't lazy—it's a new kind of discipline focused on design, architecture, and clear communication rather than syntax. Reading Code vs. Writing Code: A New Skill Set "AI is able to write really good code, if you just know how to read it... But I do not write any code. I haven't written a single line of code in a long time." Elina's approach reveals an important insight: the skill shifts from writing code to reading and validating it. She treats Claude Code as a highly skilled companion that she needs to communicate with extremely well. This requires knowing "what good looks like"—her 15 years of experience as a designer gives her the judgment to evaluate what the AI produces. She maintains dialogue throughout development, using checkpoints to verify direction and clarify requirements. The fast feedback loop means when she fails to explain something clearly, she gets immediate feedback and can course-correct instantly. This is fundamentally different from traditional development where miscommunication might not surface until weeks later. The Anti-Pattern: Letting AI Run Rampant "You need to be really specific about what you want to do, and how you want to do it, and treat the AI as this highly skilled companion that you need to be able with." The biggest mistake Elina sees is treating AI like magic—giving vague instructions and expecting it to "just figure it out." This leads to chaos. Instead, developers need to be incredibly specific about requirements and approach, treating AI as a skilled partner who needs clear communication. The advantage is that the ...