Usage

Documentation Index

Fetch the complete documentation index at: https://docs.coderabbit.ai/llms.txt

Use this file to discover all available pages before exploring further.

Know what CodeRabbit Agent for Slack has been doing across your workspace. The Usage view answers the questions that matter after rollout: what ran, when, who triggered it, which handled it, how much runtime it used, and where to dig deeper.

​

Who can see usage

Usage visibility depends on role:

​

What the table shows

​

What agent minutes mean

Agent minutes are the runtime unit CodeRabbit Agent uses for usage tracking and billing. For each run, CodeRabbit measures how long the run spent working in the sandbox, stores that time in seconds, and shows it in the UI as minutes. This is a runtime metric, not a token metric. It reflects the duration of the Agent run while work is in progress, so it is easier to understand and closer to how CodeRabbit Agent usage is governed in the product. In practice:

• Short runs use fewer agent minutes than long runs.
• Automation runs and human-triggered runs are measured the same way.
• Values can be fractional because the underlying runtime is recorded in seconds and then converted to minutes for display.

​

Trial Agent Minutes

Some workspaces receive an included Agent Minutes grant during their Agent trial. The Usage view uses the same agent-minute metric for both trial and paid usage, so trial runs still appear with their measured runtime. When a trial grant is exhausted or expires, CodeRabbit Agent pauses new work for that workspace and asks an admin to activate the Agent plan before runs can continue.

​

Human vs. automation runs

Usage shows both human-triggered and automation-triggered runs in the same view:

• Human runs appear when someone mentions @coderabbit, uses a slash command, or sends CodeRabbit Agent a direct message.
• Automation runs appear either on their configured schedule or when a matching message triggers them. They show the automation name and the channel where they ran.

Both types resolve to a scope the same way. Filtering by scope is the fastest way to narrow down what you are looking for, and filtering by agent minutes helps you spot unusually short or unusually long runs.

​

Common actions from Usage

From the Usage view, teams can:

• Open the related thread review for full run detail
• Jump back to the original Slack conversation
• Confirm which scope handled a request
• Review recent workspace activity without searching Slack first
• Trace an unexpected result back to its scope, triggering user, and execution detail

​

Filtering and navigation

The Usage view supports text search across scope names and triggering users, scope-based filtering to focus on a specific team or channel, agent-minute filtering for minimum and maximum runtime, and sorting by time, agent minutes, scope, or user. Results are paginated so you can browse recent and historical runs without loading everything at once.

​

What’s next