Interactive Mode - Claude Code
Real-time prompt loop with history, completions, and multiline input.
Interactive mode is the default Claude Code experience - a persistent prompt where you type, Claude runs tools, and you iterate turn by turn.
What it does
The interactive loop handles input, tool calls, and streaming output in one session. It supports command history, multiline prompts, tab completion, and inline UI for permission dialogs. You can switch models, toggle plan mode, open the transcript viewer, or drop to a bash shell without leaving the loop.
When to use it
- Most day-to-day coding work where you want to review each step.
- Long debugging sessions where conversation state matters.
- Exploring a new codebase with back-and-forth refinement.
- Any task where headless mode would be overkill.
Gotchas
- The prompt buffer is per-session - moving between projects loses the last draft unless you use command history.
- Multiline paste behavior depends on your terminal; if newlines get flattened, enable bracketed paste.
- Some shortcuts collide with terminal multiplexer bindings. Check your tmux config if Ctrl+B conflicts.
Official docs: https://code.claude.com/docs/en/interactive-mode.md
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools - delivered free every week.
Was this helpful?
