The rise of the professional vibe coder (a new AI-era job)

Lazar Jovanovic, who calls himself a professional vibe coder and was the first official vibe coding engineer at Lovable, explains how he builds internal and external products with AI tools despite having no formal coding background. The conversation covers his planning-first workflow, techniques for getting clarity and context to AI agents, debugging methods, and his views on how PM, engineering and design roles are converging.

01Key learnings

• Start a project with several parallel attempts (brain dump, typed prompt, design reference, code template) to find the strongest direction before committing tokens.
• Spend most of your time planning and chatting with the AI rather than executing, since clarity matters more than raw build speed.
• Write a set of source-of-truth docs (master plan, implementation plan, design guidelines, user journeys, tasks.md) so the agent has persistent context.
• Keep agent context small by giving it one task at a time and pointing it to specific files, since token windows are limited and agents over-read when vague.
• When stuck, escalate in order: ask the tool to fix, add console logs for awareness, use an external reviewer like Codex, then revert and rephrase the prompt.
• After solving a bug, ask the agent how you could have prompted better and write those lessons into its rules file so you stop repeating the mistake.
• Invest in taste and judgment: study great design, learn design vocabulary, and expose yourself to exceptional work, since good-enough output is now commoditized.
• Build in public and ship real projects as proof of skill; Lazar credits this for getting hired and suggests applicants send a working app instead of a résumé.

02Frameworks mentioned

Summary and takeaways written by PM Atlas; quotes are short excerpts. © the original author.