Agentic coding
A development style centred on coding agents — the human describes intent, the agent plans and executes the work, and the human reviews diffs or PRs rather than authoring code line by line. The umbrella term for vibe coding and adjacent practices.
Background
Agentic coding shifts the developer's role from author to reviewer/director. Workflows include: prompting an agent with a feature spec, watching the agent edit files and run tests, intervening when it stalls, and accepting/rejecting PRs. Distinct from autocomplete (per-line suggestions) and from chat-based assistants (single-turn answers). The term is broader than vibe coding, which specifically de-emphasises reading the generated code.
Tools that use it
- 01→OpenHands
Open-source autonomous coding agent platform, formerly OpenDevin, by All Hands AI.
- 02→Devin
Cognition's autonomous software engineer — runs tasks in a managed cloud sandbox with browser, terminal, and editor.
- 03→Claude Code
Anthropic's official CLI agent for Claude — runs in the terminal, edits files, executes commands, and ships PRs.
- 04→Windsurf
AI code editor by Codeium with Cascade agent for autonomous multi-step coding tasks.
- 05→Cursor
AI code editor forked from VS Code with built-in agent, multi-file edits, and tab-completion.