Lenny's Podcast: Product | Career | Growth
--% time saved
PodcastLenny's Podcast: Product | Career | Growth
Publisher/creatorLenny Rachitsky
Shortcast updated
About this episode
Lazar Jovanovic is a full-time professional vibe coder at Lovable. His job is to build both internal tools and customer-facing products purely using AI, while not having a coding background. In this conversation, he breaks down the tactics, workflows, and framework that let him ship production-quality products using only AI. We discuss: 1. Why having no coding background can be an advantage when building with AI 2. Why most of your time should go to planning and chat mode, not prompting 3. What to do when you get stuck: his 4x4 debugging workflow 4. The PRD and Markdown file system that keeps AI agents aligned across complex builds 5. Why kicking off four or five parallel prototypes is the best way to clarify your thinking 6. Why design skills and taste are going to be the most important skills in the future 7. His “genie and three wishes” mental model for making the most of AI’s limitations 8. How product, engineering, and design roles are converging—and what that means for your career — Brought to you by: Strella —The AI-powered customer research platform: https://strella.io/lenny Samsara —Saving lives with AI built for physical operations: https://samsara.com/lenny WorkOS —Modern identity platform for B2B SaaS, free up to 1 million MAUs: https://workos.com/lenny — Episode transcript: https://www.lennysnewsletter.com/p/getting-paid-to-vibe-code — Archive of all Lenny's Podcast transcripts: https://www.dropbox.com/scl/fo/yxi4s2w998p1gvtpu4193/AMdNPR8AOw0lMklwtnC0TrQ?rlkey=j06x0nipoti519e0xgm23zsn9&st=ahz0fj11&dl=0 — Where to find Lazar Jovanovic: • X: https://x.com/lakikentaki • LinkedIn: https://www.linkedin.com/in/lazar-jovanovic • YouTube: https://www.youtube.com/@50in50challenge • Starter Story course: https://build.starterstory.com/build/ai-build-accelerator?via=lazar (code LAZAR15 for 15% off) — Where to find Lenny: • Newsletter: https://www.lennysnewsletter.com • X: https://twitter.com/lennysan • LinkedIn: https://www.linkedin.com/in/lennyrachitsky/ — In this episode, we cover: (00:00) Introduction to Lazar and professional vibe coding (04:53) What a professional vibe coder actually does day-to-day (09:26) Why non-technical backgrounds can be an advantage (12:24) The importance of self-awareness (14:42) His “genie and three wishes” mental model (17:43) Developing taste and judgment in the age of AI (21:46) The parallel project approach for better outcomes (29:30) Creating dynamic context windows with PRDs (36:56) Why elite vibe coders focus on planning, not coding (44:43) Creating MD files to guide AI development (50:57) Why prototyping still matters (56:50) Why “good enough” is no longer good enough (01:00:53) The future of engineering in an AI world (01:05:14) What to do when you get stuck: his 4x4 debugging workflow (01:14:27) Helping agents learn from their mistakes (01:15:35) Why watching agent output is more important than code (01:19:08) The incredible pace of AI development (01:22:55) Why emotional intelligence will become more valuable (01:28:30) How to become a professional vibe coder (01:30:10) Why building in public is the fastest path to opportunities (01:37:03) Final thoughts on focusing on quality over tech stack — Referenced: • The new AI growth playbook for 2026: How Lovable hit $200M ARR in one year | Elena Verna (Head of Growth): https://www.lennysnewsletter.com/p/the-new-ai-growth-playbook-for-2026-elena-verna • Elena Verna on how B2B growth is changing, product-led growth, product-led sales, why you should go freemium not trial, what features to make free, and much more: https://www.lennysnewsletter.com/p/elena-verna-on-why-every-company • The ultimate guide to product-led sales | Elena Verna: https://www.lennysnewsletter.com/p/the-ultimate-guide-to-product-led • 10 growth tactics that never work | Elena Verna (Amplitude, Miro, Dropbox, SurveyMonkey): https://www.lennysnewsletter.com/p/10-growth-tactics-that-never-work-elena-verna • Lovable: https://lovable.dev • Lovable + Shopify: https://lovable.dev/shopify • Everyone’s an engineer now: Inside v0’s mission to create a hundred million builders | Guillermo Rauch (founder and CEO of Vercel, creators of v0 and Next.js): https://www.lennysnewsletter.com/p/everyones-an-engineer-now-guillermo-rauch • Mobbin: https://mobbin.com • Dribbble: https://dribbble.com • 21st.dev : https://21st.dev • Lovable base prompt generator: https://chatgpt.com/g/g-67e1da2c9c988191b52b61084438e8ee-lovable-base-prompt • Lovable PRD generator: https://chatgpt.com/g/g-67e1e85fbeac8191a69b95c6d5c42ef6-lovable-prd-generator • Felix Haas’s newsletter: https://designplusai.com • Bauhaus: https://en.wikipedia.org/wiki/Bauhaus • Glassmorphism: https://www.figma.com/community/plugin/1197106608665398190/glassmorphism • UI style guide: http://uistyle.lovable.app • Cloudflare: https://www.cloudflare.com • Ben Tossell on X: https://x.com/bentossell • The rise of Cursor: The $300M ARR AI tool that engineers can’t stop using | Michael Truell (co-founder and CEO): https://www.lennysnewsletter.com/p/the-rise-of-cursor-michael-truell • Peter Thiel says AI will be ‘worse’ for math nerds than for writers: https://www.businessinsider.com/peter-thiel-ai-worse-for-math-professionals-than-writers-2024-4 • Andrej Karpathy on X: https://x.com/karpathy • The 100-person AI lab that became Anthropic and Google’s secret weapon | Edwin Chen (Surge AI): https://www.lennysnewsletter.com/p/surge-ai-edwin-chen • Why experts writing AI evals is creating the fastest-growing companies in history | Brendan Foody (CEO of Mercor): https://www.lennysnewsletter.com/p/experts-writing-ai-evals-brendan-foody • Slumdog Millionaire : https://www.imdb.com/title/tt1010048 — Production and marketing by https://penname.co/ . For inquiries about sponsoring the podcast, email [email protected] . — Lenny may be an investor in the companies discussed. To hear more, visit www.lennysnewsletter.com
Loading episode data...
Episode summary
Today’s guest is Lazar Yovanovich, a professional vibe coder at Lovable, and yes, this is that dream role where you build with AI all day at a top tier level.
I turned this into a career by building in public, and in a world where code writing becomes rare like calligraphy, you can hire yourself first and let the work speak.
We kick off with a theme you’ll hear all hour: AI is an amplifier, so clarity in the ask matters more than ever.
Think Aladdin and the genie; vague wishes backfire, so I optimize for judgment, taste, and precise intent over raw output.
Set the stage for us—what do you actually ship, and where do you focus your time?
I build across the company, from public templates and a merch store to custom internal tools like feature adoption dashboards, and I default to build over buy when I can move faster and keep quality.
And you roam across teams rather than sitting in one lane, right?
Exactly; I started in growth, then became a fast-response builder for go-to-market, enterprise needs, and community, taking rough ideas to production quickly.
You’ve said not having a traditional engineering background can be an edge—why?
I don’t carry old constraints, so I try “impossible” things like Chrome extensions or video generation and often discover they’re doable; a little positive delusion helps.
The two traps for non-technical folks are getting stuck and shipping fragile slop; how do you avoid both?
I spend most of my time planning in chat, then execute; there are two bottlenecks to respect—the model’s context window and our human vagueness—so I get specific, provide references, and steer one scoped task at a time.
Walk us through your clarity system; what do you actually do at the start?
I spin up several builds in parallel: a voice brain dump, a refined brief, a pass with strong visual references, and one seeded with code snippets so the agent can mirror exact structure and style.
Counterintuitive and great; you explore fast, pick a winner, and avoid grinding on a bad first take.
Totally; it feels like more credits up front, but it saves days later by reducing rework and design drift.
You also juggle several projects without losing the thread; how?
I make dynamic context: a master plan for why and for whom, an implementation plan for order of work, design guidelines for look and feel, user journeys for flow, then a tasks file the agent follows, plus rules that force it to read those docs before acting.
So you plan for a day, then let the agent march task by task to stay within its memory limits.
Right; I mostly read agent output, keep docs fresh, and reserve my energy for judgment, copy, and design choices like typography that shape the final feel.
For folks who want to try your file setup, can they start with templates?
Yes; search for my Lovable PRD generator on ChatGPT, brain dump, and it will produce the core files you can drop into your project.
You argue the winners now are PMs and soon designers, because humans decide what to build and what feels magical.
Good enough is everywhere, so the delta is taste; I learned from elite designers that what looks simple can be fifty layered moves, and I study styles and prompts to recreate that level.
What about engineers—does this future leave them behind?
We’ll need elite engineers more than ever to scale, secure, and maintain systems; building is one skill, expanding and operating is another.
You’ve said coding by hand becomes art while everyone else engineers through agents, and the classic PM–design–engineering circles are merging.
Exactly; we’ll all be some flavor of AI-powered builder, and code-as-craft will become rare and celebrated.
When things break, what’s your unblocking playbook?
I run a four by four: try the tool’s auto-fix, surface the issue with console logs so the agent can see it, pull in an external reviewer like OpenAI Codex or compress the repo for a deep read, then roll back a few steps and re-prompt calmly.
And you turn each fix into future leverage.
I ask how I could have prompted better and bake that guidance into rules so the agent remembers and I don’t need to.
You also learn by reading the agent’s thinking layer, not by reading code.
Yes; the layer above code is the conversation, and knowing what is possible matters—I once chased an image feature before the API existed, and waiting a week would have solved it.
These tools evolve fast, so workflows you hand-built last year are now native buttons; the skill that compounds is judgment.
We’re offloading drudgery and getting paid to think; powerful tools punish fuzzy directions, so clarity first, then build.
For career durability, where should people invest?
Double down on human skills—tasteful design, sharp copy, and emotional insight; AI devours deterministic tasks like translation but amplifies distinctive voices and craft.
How did you land this role, and how can others?
My path was messy, but I shared everything, shipped in public, joined hackathons, and treated vibe coding as a profession before anyone hired me; companies now even list Lovable skills in job posts.
Your closing note was pure energy: stop listening and go build.
Lovable feels like a mission, not just a product; going from consumer to creator is electric, and fear flips to excitement the moment you ship anything.
Before we go, any final guidance?
The stack matters less than the experience; invest in exposure time, read agent output, follow great designers, and aim for magic, not just good enough.
Find Lazar on LinkedIn and YouTube, send him feedback on your first build, and if this resonated, check Lovable’s open roles; thanks for listening and see you next time.
Ready to save time?
Download Shortcast and get started today