Overview
Every task, whatever started it, has a task page. The page is where you watch the work, interrupt it, answer it, and decide what to do with what it produced. It has its own address, so you can close it and come back, or send the link to someone else on your team.Follow the work
The task page shows the current state of the run alongside three live views.
Activity. A running feed of what the agent is doing, grouped by kind:
When you reopen a task that is still running, the page replays its recent activity: up to 200 events from the last 15 minutes.
Live diff. The changes made so far, updating as the agent works. You don’t have to wait for the task to finish to see where it’s going.
Presence. Who else is looking at the task right now, so two people don’t steer it in opposite directions.
A task link can point at a task in a different organization from the one you have selected. CodeRabbit resolves the owning organization and switches your context when you have access to it.
Inspect the workspace
The task works in a prepared, isolated checkout of your repository. You can look inside it:- Files — browse the checkout the agent is working in, and reference files back to it in your next message.
- Command output — the work the agent did at the terminal, surfaced in the activity feed.
- Browser — when the task runs something with a web interface, open its viewer and navigate it yourself. Viewer activity keeps the session alive while you’re using it.
Edit a workspace file
Open a file in the workspace and choose Edit, make your changes, then Save. Editing is available while the agent is idle; wait for the current turn to finish or cancel it first. Saved edits change the task’s sandbox. Review them in the diff and deliver the changes when they are ready. If the file changes after you open it, the editor keeps your draft and reports the conflict so you can review the latest contents before saving again.Steer the task
You do not have to wait for a turn to end to change its direction.
Queued messages are ordinary follow-up turns, so normal billing applies to them. See Access and billing.
Use
/skill to choose a skill for a follow-up. A message with a selected skill is queued for its own turn, so it can run after the current work finishes.
Schedule a follow-up
Use/schedule in an existing task’s composer to open Scheduled tasks, then choose Create scheduled task. Give it a name and a prompt, choose an interval or a calendar schedule, and check the timezone before saving.
Scheduled prompts run in the same task, keeping its conversation and repository context. Use them for recurring checks, such as following a pull request’s progress or checking whether a blocker has cleared. Normal access and billing checks still apply to each run.
Return to Scheduled tasks to edit, pause, resume, or delete a schedule. A schedule can also pause when its completion condition is met or it needs your input; check the displayed reason before resuming it.
Answer a question
When the agent needs something only you know — which of two behaviors is intended, whether a migration is safe — it raises the question on the task page and waits. Answer it there and the run continues with your answer as context.Review a plan
In plan mode the agent writes an implementation plan and stops. Plans are versioned, so a revision supersedes the previous one rather than editing it in place. You have three responses:
A Coding Agent plan is not the same thing as a Coding Plan, which is CodeRabbit’s separate planning product. A Coding Agent plan lives inside one task and gates that task’s implementation.
Review the proposed patch
With manual delivery, a finished task produces a proposed patch for you to review before pushing. If you enable Autopilot, you authorize automatic publication and follow-up fixes instead.- Read the diff, in full or as it was being built.
- Comment on a line, on either side of the diff — the new-file side for something the agent added, the old-file side for something it removed.
- Request a revision, and the agent produces a new proposal.
- Reject the proposal if the approach is wrong.
- Accept it and choose how it lands. See Deliver a task’s changes.
Address CodeRabbit’s review comments
Once a task’s changes are on a pull request and CodeRabbit has reviewed them, unresolved CodeRabbit findings can go straight back to the same task. It collects the open review comments and runs a follow-up turn against them, keeping all the context it already has instead of starting over.Stop a task
Cancel a running task from its page. Cancellation stops the current turn; the task, its history, and anything it already delivered remain.Find your tasks
Your organization’s tasks are listed at app.coderabbit.ai/code/tasks, grouped by what they need from you: tasks that are working, tasks waiting on a person’s decision or input, tasks that completed, and tasks that failed. Filter the list by what started each task: Chat, Finishing touch, Issue Plan, Prompt, Merge conflict, CR comment, or Security fix. Archive an idle task to take it out of the ordinary list. Archiving is a visibility marker only — it doesn’t change whether the task completed or failed, and it can’t be applied to a task with a turn in progress. Include archived tasks in the filter to see them again, or unarchive one to return it to the list unchanged.Control who can see a task
A task is visible to your team by default. Switch it to private and its prompts, files, activity, and attachments become visible only to you — including to anyone following a direct link to it. Only the task’s author can change this, and it can be changed back at any time. To create a task private from the start, use the/private slash command in the composer.
What’s next
Deliver a task's changes
Choose how accepted changes land, and what to do when delivery is blocked.
Access and billing
Understand which turns are free, how agent minutes are metered, and how the monthly cap behaves.
Start a coding task
Every way to start a task and where each one is available.