Once your workspace is set up, most day-to-day use happens directly in Slack. You can start with anDocumentation Index
Fetch the complete documentation index at: https://docs.coderabbit.ai/llms.txt
Use this file to discover all available pages before exploring further.
@coderabbit mention in any channel or thread, or open the CodeRabbit app to chat directly. Slash commands are also available for specific actions.
Entry points
| Entry point | What it does | Details |
|---|---|---|
@coderabbit mention | Investigate, explain, plan, or act on anything in the current conversation. The run uses the matching the current channel, thread, or DM. | Scopes |
| Direct conversation | Open CodeRabbit from Slack’s Apps sidebar or search for “CodeRabbit” in Slack. The Chat tab shows starter prompts when empty and does not require an @mention — just type your message. | — |
Slash commands
Slash commands provide shortcuts for specific actions. You can also trigger all of these actions by asking@coderabbit directly.
| Command | What it does | Details |
|---|---|---|
/plan | Generate a structured implementation plan from a request or thread. | Plans |
/learn | Capture a durable fact from the current thread or from text you provide directly. | Knowledge Base |
/automations | List, create, or manage scheduled and message-triggered automations for the current channel. | Automations |
How conversation behavior works
CodeRabbit Agent behaves differently depending on the Slack surface:- Direct conversations
- Channel threads
Open CodeRabbit from the Apps sidebar or search for “CodeRabbit” in Slack to start a direct conversation. Each top-level message starts a new conversation. Threaded replies continue that same conversation. There is no need to @mention the bot — it stays active automatically.
What determines what CodeRabbit Agent can use
Each run is governed by the scope that matches the current Slack surface. That scope determines:- Which repositories are available
- Which connections can be used
- What spend limit applies
- Whether the shared sandbox is available
- Whether knowledge should be shared or private
Who can use CodeRabbit Agent
CodeRabbit Agent responds to workspace members only.After a run
After completing a task, the Agent replies in the thread with its findings, a proposed plan, follow-up actions like opening a PR, or an offer to save what it learned to the Knowledge Base. For deeper inspection, the companion web app provides thread reviews for run-by-run execution detail, usage for workspace-wide activity, and plans for version comparison and agent handoff.Slack vs. the web app
| Use Slack when you want to… | Use the web app when you want to… |
|---|---|
| Ask CodeRabbit Agent to investigate, plan, learn, or act in context | Inspect what happened after a run in more detail |
| Manage automations from the conversation where they apply | Configure scopes, connections, or sandbox settings |
| Confirm knowledge proposals from the same thread | Browse knowledge history, plans, usage, and thread review artifacts |
What’s next
Scopes
Learn how CodeRabbit Agent decides which repositories, tools, and limits apply in each conversation.
Automations
See how recurring CodeRabbit Agent tasks work for channels and other Slack surfaces.
Plans
Review how planning work moves from Slack into a structured implementation plan and handoff flow.