Vibe coding
- Definition
- A development approach where a programmer describes what they want in natural language and iterates with an AI coding assistant to produce working software, relying on the AI for implementation details rather than writing code line by line.
- Why it matters
- Vibe coding is redefining who can build software. When a product manager, designer, or domain expert can describe a feature in plain English and get working code, the traditional bottleneck of 'we need more engineers' weakens significantly. This is not theoretical: founders are shipping production applications using Cursor, Claude Code, and Replit Agent with minimal traditional coding. The implications for the software industry are profound: engineering talent scarcity decreases, time-to-market compresses, and the barrier between 'idea person' and 'builder' dissolves. The risk: vibe-coded software may work but lack the quality, security, and maintainability of expert-written code, creating technical debt that is invisible until it isn't.
- In practice
- Andrej Karpathy coined the term 'vibe coding' in early 2025, describing his own practice of using AI to write code while he focuses on guiding the direction. Cursor reached $100M+ ARR as the leading vibe coding IDE. Replit Agent and Bolt.new enable non-programmers to build applications entirely through natural language. Y Combinator's 2025 batch included multiple companies where solo founders built their entire codebase through AI-assisted development. The debate: experienced engineers use vibe coding to move faster while maintaining code quality through review, while non-engineers produce working prototypes that may need significant refactoring for production use.
We cover products & deployment every week.
Get the 5 AI stories that matter — free, every Friday.
Related terms
Co-pilot
An AI assistant that works alongside a human user within an existing workflow, providing suggestions, automating sub-tasks, and augmenting productivity while keeping the human in control of final decisions.
Agent
An AI system that can autonomously plan, use tools, and execute multi-step tasks on behalf of a user. Agents are the next major product paradigm after chatbots, with every major lab shipping agent frameworks.
One-person unicorn
A concept where a solo founder or tiny team can build a billion-dollar company by leveraging AI to automate functions that previously required large teams, including engineering, design, marketing, customer support, and operations.
AI-native
A company or product built from the ground up around AI capabilities, rather than bolting AI onto legacy software. AI-native startups often have fundamentally different cost structures and GTM motions.
Know the terms. Know the moves.
Get the 5 AI stories that matter every Friday — free.
Free forever. No spam.