The rise of the professional vibe coder (a new AI-era job) | Lazar Jovanovic (Professional Vibe Coder)
Key insights
Media referenced
- Slumdog Millionaire - movie - Lazar compares his non-linear career path (blue-collar jobs, forestry engineering, community management) to the film's storyline, where every prior experience turns out to prepare the character for the moment that matters.
Companies
- Lovable - Lazar's employer; he is Lovable's first official vibe coding engineer, shipping both internal tools and public-facing products (Shopify integration templates, the company merch store) using the tool itself.
- Cursor - Referenced repeatedly as an alternative AI coding tool with the same context-window and clarity constraints as Lovable.
- Claude Code - Cited as one of the agentic coding tools where the same rules.md/agent.md and context-management workflow applies.
- OpenAI Codex - Lazar's go-to external tool for deep debugging - he exports code to GitHub, imports it into Codex, and uses it purely for diagnosis, not for making changes.
- ChatGPT - Used for chat-mode brainstorming, drafting PRDs, and running Lazar's own custom GPTs that generate his master-plan/PRD templates.
- RepoMix - A tool Lazar uses to compress an entire codebase into a single file so he can paste it into Claude or ChatGPT as an external diagnostic consultant.
- Strella - Podcast sponsor; an AI-moderated user-research platform used by teams like Amazon and Duolingo.
- Samsara - Podcast sponsor; builds AI/edge hardware and software for physical-world industries (trucking, construction, first responders).
- WorkOS - Podcast sponsor; provides drop-in enterprise-readiness APIs (SSO, SCIM, RBAC, audit logs) for B2B SaaS.
- Shopify - Lovable shipped a Shopify integration; Lazar personally vibe-coded Lovable's merch store to prove the integration works.
Techniques and frameworks
- Parallel prototyping (the four-start method) - Before committing to a direction, Lazar starts up to four parallel builds from the same idea: a raw voice brain-dump, a more deliberate typed prompt, a design reference pulled from Mobbin/Dribbble, and a code snippet from a component library like 21st.dev - then picks the clear winner.
- Layered PRD/context system - A stack of markdown files - masterplan.md (why/who), an implementation plan (build order), design-guidelines.md, a user-journey doc, and tasks.md - that gives the AI agent persistent reference material so Lazar can stop re-explaining context and just say 'proceed with the next task.'
- rules.md / agent.md project knowledge files - Standing instructions the agent reads before every task (read all PRDs first, check tasks.md for the next task, report back what it did and how it tested) so behavior doesn't need to be re-specified per prompt.
- Four-by-four debugging framework - A four-step escalation when something breaks: (1) use the tool's own 'try to fix' button once, (2) add console logging yourself to give the agent awareness, (3) escalate to an external tool like Codex or RepoMix+ChatGPT purely for diagnosis, (4) revert and re-prompt more clearly since most failures trace back to an unclear ask - then codify the lesson into rules.md.
- Exposure time - A concept Lazar credits to Guillermo Rauch: deliberately spending more time consuming great design, copy, and prompting examples than building, since the ceiling on AI output is what you exposed the model (and yourself) to before it acts.
Summary
Lazar Jovanovic is, by his own description, the first person hired at Lovable with the explicit title of vibe coding engineer - a self-taught, non-technical builder who spends his full-time job shipping internal and external products entirely through AI coding tools like Lovable, having never written a line of code by hand. The conversation opens by dismantling a common assumption: that a technical background is an advantage when working with AI coding tools. Lazar argues the opposite - not knowing what "shouldn't" be possible let him build things (Chrome extensions, desktop apps, in-app video generation on Lovable before it was a supported feature) that technically-minded people ruled out in advance. He calls this staying "positively delusional," paired with enough self-awareness to know the real bottleneck isn't code generation but clarity of the ask.
Much of the episode is a practical workflow breakdown. Lazar starts new projects by running several parallel prototypes from the same idea - a raw voice brain-dump, a more deliberate typed prompt, one seeded with a design reference pulled from Mobbin or Dribbble, and one seeded with an actual code snippet - because AI tools interpret code and visual references far more reliably than natural language alone. Once a direction is clear, he shifts into what he calls the planning phase: building a stack of markdown documents (a master plan, an implementation plan, design guidelines, a user-journey doc, and a granular tasks.md) plus standing rules.md/agent.md instructions that tell the agent how to behave without re-explaining context every time. This is what lets him run five or six Lovable projects simultaneously - once the documentation exists, his own prompts shrink to "proceed with the next task," and he spends his attention reading agent output rather than writing code or micromanaging execution.
He frames the AI context window through a genie-and-Aladdin metaphor: ask vaguely and you get a technically-correct but useless result, the way a genie who grants "taller" makes you thirteen feet tall. Token budget is treated as the truly scarce resource, split between reading references, thinking, and executing, so unclear prompts waste most of it on disambiguation. When something breaks, he uses a fixed four-step escalation - the tool's own fix button, manually added console logging to build the agent's awareness, an external diagnostic pass through OpenAI's Codex or a RepoMix-compressed codebase pasted into ChatGPT or Claude, and finally reverting and re-prompting on the assumption that most persistent bugs trace back to his own unclear ask. After any fix, he has the agent write the lesson directly into rules.md so it never has to be re-taught.
The back half of the conversation turns to where this leaves human skill. Lazar's central claim is that AI has collapsed the cost of "good enough" output to near zero, so the competitive gap has shifted entirely from functional-versus-broken to good-versus-world-class, and closing that gap requires taste the model doesn't supply on its own. He credits Guillermo Rauch's concept of "exposure time" - deliberately consuming great design and copy rather than only building - as the practice that develops judgment, and describes discovering that a "simple" gradient he admired was actually fifty layered colors, a moment that reset his sense of what quality actually requires. He predicts hand-written code becomes a rare, admired craft like calligraphy, that elite engineering remains essential for the infrastructure everyone else builds on top of, and that PM, engineering, and design converge into a single AI-assisted builder role - with designers, not engineers, likely the next big winners, since AI is improving faster at technical decisions than emotional ones.
On career path, Lazar's advice is to build in public rather than wait to be hired: his own route into Lovable came from documenting failures and workflows on YouTube and LinkedIn before the company approached him, and he notes candidates have gotten hired by sending a working Lovable app in place of a resume. His closing framing is unusually optimistic relative to the anxiety many builders express about AI: he sees the shift as finally letting people get paid for clarity and judgment - the parts of work most people actually enjoy - rather than for repetitive execution.
Notable Quotes
"Coding is going to be like calligraphy. It's going to be so rare that it's going to become an art." - Lazar Jovanovic
"We won't be rewarded in the world of AI for faster raw output. We will be rewarded for better judgment." - Lazar Jovanovic
"If a tool is super powerful and you give it a wrong input, the output's going to suck as well." - Lazar Jovanovic
"It feels like an emerging core skill is learning clarity in the ask of the AI." - Lenny Rachitsky
"AI is never going to write good comedy. It's impossible. It just doesn't have that layer." - Lazar Jovanovic