The rise of the professional vibe coder (a new AI-era job) | Lazar Jovanovic (Professional Vibe Coder)

2026-02-01 · Source: Lenny's Podcast: Product | Career | Growth · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Project & Product Management · Depth: Advanced, extended

Summary

Lazar Jovanovic, a professional "vibe coder" at Lovable, builds internal tools and customer-facing products using AI without a traditional coding background. He emphasizes that a non-technical background can be an advantage, fostering a "positively delusional" mindset where everything is possible until proven otherwise. Jovanovic dedicates 80% of his time to planning and chat mode, and only 20% to execution, optimizing for clarity and judgment over raw speed. He advocates for parallel prototyping, starting four to five projects simultaneously to clarify ideas and compare design options, which ultimately saves time and resources. His workflow involves creating detailed Product Requirements Documents (PRDs) and Markdown files to provide dynamic context to AI agents, ensuring alignment and efficient execution, especially when dealing with the AI's limited context window.

Key takeaway

For AI Product Managers or Software Engineers aiming to build high-quality products with AI, focus on developing exceptional clarity, design taste, and judgment. Implement a structured planning phase using detailed PRDs and Markdown files to guide AI agents, treating them as human collaborators. This approach, including parallel prototyping and dynamic context management, will significantly reduce development time and improve output quality, allowing you to build "world-class" solutions rather than just "good enough" ones.

Key insights

Effective AI-driven development prioritizes clarity, planning, and design judgment over traditional coding skills.

Principles

• Non-technical backgrounds can foster unbiased AI building.
• Optimize for clarity and judgment, not raw output speed.
• Treat AI tools as technical co-founders and educators.

Method

Start multiple parallel prototypes to explore ideas, then create detailed PRDs and Markdown files (master plan, implementation plan, design guidelines, user journeys, tasks.md, rules.md) to provide dynamic context and guide AI agents through specific, sequential tasks.

In practice

• Use voice dictation for initial "brain dump" prompts.
• Reference design sites like Mobbin or Dribbble for visual input.
• Ask AI agents to generate PRDs and task lists for project planning.

Topics

• AI Product Development
• AI Workflows
• Prompt Engineering
• AI Debugging
• Future of AI Roles

Best for: Prompt Engineer, AI Product Manager, Software Engineer

Related on AIssential

• Day 1 - Agentic Engineering/VIbe Coding an AI App from Zero To Production | 🔴 Live — AI-driven interview skills can efficiently flesh out complex application specifications and product requirements.
• Vibe-Coding an Attention Firewall, w/ Steve Newman, creator of The Curve — Custom AI tools and "vibe-coding" workflows enhance personal productivity and manage information overload.
• Vibe Coding's Uncanny Valley [Alexandre Pesant] - 752 — AI-assisted "vibe coding" is rapidly evolving, enabling non-technical users to build applications through natural language.
• Vibe coding and agentic engineering are getting closer than I'd like — The increasing reliability of AI coding agents blurs the distinction between casual "vibe coding" and professional "agentic engineering."
• What I Learned Vibe Coding Apps as a Non-Coder — AI-driven "Vibe Coding" empowers non-coders to prototype rapidly but introduces new complexities for production-grade applications.
• Extra #4 - Beyond “Vibe Coding”: Evolution of AI Development — Spec-Driven Development (SDD) offers a structured approach to manage LLMs, moving beyond unstructured "vibe coding."

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Lenny's Podcast: Product | Career | Growth.