Agent overview

The agent is the core of 4RGE. You describe what you want in natural language; the agent gathers context from your codebase, runs tools, and edits files — pausing for your approval at the moments that matter.

Whether you are fixing a bug locally, refactoring a service, or delegating a long task to a cloud agent, the same agent loop applies: understand the request, take action through mediated tools, and verify the result before you accept changes.

How Agent works

An agent is built on three components:

1. Instructions — The system prompt and rules that guide agent behavior
2. Tools — File editing, codebase search, terminal execution, and more. See Tools.
3. Model — The agent model you pick for the task. Your org controls availability in Model control.

Checkpoints

Checkpoints save snapshots of your codebase during an agent session. The agent automatically creates them before making significant changes, capturing the state of all modified files.

If the agent takes a wrong turn, click any checkpoint in the chat timeline to preview your files at that point, then restore to revert all files to that state. You can also restore from the Restore Checkpoint button on previous requests or the + button when hovering over a message.

Checkpoints are useful for exploratory work, complex refactoring, and iterative development where you want safe rollback points.

Using the queue

1. While the agent is working, type your next instruction
2. Press Enter to add it to the queue
3. Messages appear in order below the active task
4. Drag to reorder queued messages as needed
5. The agent processes them sequentially after finishing the current task

Keyboard shortcuts

• Press Enter while the agent is running to queue your next message instead of interrupting the current task
• Press ⌘K (or Ctrl K) to search documentation while you work
• In the agent panel, refer to files with @filename when your build supports it — the agent prioritizes those paths