Vibe coding
A programming workflow where a developer prompts an AI coding agent in natural language and reviews the intent of the output rather than the syntax.
Coined by Andrej Karpathy in a February 2025 social-media post, "vibe coding" describes a style of software development in which an AI agent with tool-use capabilities (Claude Code, Codex, Cursor, Gemini CLI) writes and edits files on the developer's behalf while the developer reviews outcomes — running the program, checking tests, watching the dev server — rather than reading every diff line-by-line.
Vibe coding is distinct from three adjacent workflows. AI autocomplete (tab-to-accept in an editor) keeps the human in the typing loop. LLM pair programming (chat with ChatGPT, paste into editor) keeps the human in the edit-boundary loop. Agentic refactors where every diff is read still count as traditional engineering. Vibe coding drops both of these guards.
The workflow has strong critics — code-provenance concerns, security drift, skill atrophy — and strong proponents, especially among solo builders and greenfield work. VibeMon is built for this workflow: it listens to what the agent does — edits, commits, passing tests — rather than to the human's keystrokes, and turns it into garden energy.
Related terms
- Garden energy — What the VibeMon garden runs on: activity from your AI coding agents — edits, commits and passing tests — turned into energy that the slime gardeners spend.
- Vibe coding activity — The activity view in the VibeMon app: coding time today, a 24-hour wave, live agent sessions and an alert when a session is waiting for you.
- Hook event — A structured message that an AI coding agent emits at a defined point in its lifecycle — after a tool runs, when a turn ends, when a session starts. VibeMon's original client was built on these events.