CodeRabbit logo
CodeRabbit Agent for Slack

Your team's second brain

One agent for your entire Software Development Lifecycle. Right in Slack.

Try for free

Get $50/user free agent minutes.

# eng-incidents
Datadog
Datadog 2:38 AM 🔴
Alert: checkout-service p99 latency > 10s
checkout-service p99 latency spiked from 380ms to 12.4s at 02:38 UTC.
Nadia K.
Nadia K. 2:41 AM
@CodeRabbit pull the Datadog traces for checkout-service and figure out where the bottleneck is.
CodeRabbit
CodeRabbit 2:41 AM
Pulled APM traces since 02:15 UTC. Every slow trace is stuck on the same downstream call, POST /api/inventory/reserve to inventory-service.

Checked GCP Cloud Run logs for inventory-service. Instance count dropped from 8 to 1 at 02:35 UTC. Autoscaler shows a config change pushed at 02:34 UTC that set maxInstances to 1. That came from PR #3301 merged earlier tonight. It was supposed to update env vars but accidentally included a Terraform change to the scaling config.
Marcus J.
Marcus J. 2:43 AM
Just saw the page. Nadia, you need a hand?
Nadia K.
Nadia K. 2:43 AM
CodeRabbit already found it. Accidental scaling change in #3301. @CodeRabbit open a revert for just the scaling config, don't touch the env var update.
CodeRabbit
CodeRabbit 2:44 AM
Done. PR #3315 opened: fix: revert inventory-service maxInstances to 12

Isolated just the scaling revert. The env var update from #3301 is untouched. Once merged, Cloud Run will scale back up within ~90 seconds.
Marcus J.
Marcus J. 2:45 AM
Merging. Nadia, watch the dashboard.
Nadia K.
Nadia K. 2:47 AM
Latency dropping. Back under 500ms. We're good.
Marcus J.
Marcus J. 2:48 AM
@CodeRabbit draft a postmortem and file it. SEV-2.
CodeRabbit
CodeRabbit 2:48 AM
Done. ENG-4120 created in Linear: "SEV-2 Postmortem: inventory-service scaling regression" with timeline, root cause, and remediation. Linked to PR #3301 and PR #3315.
BoldItalicUnderlineStrikethroughLinkOrdered listBulleted listBlockquoteCodeCode block
AddAaEmojiMentionVideoMicShortcuts
Send

From the team that pioneered AI code reviews

2M

code reviews every week

6M

repos under review

15K

customers

AI Intelligence brain illustration

Smart isn't enough

Reasoning without context is a reflex. Context without reasoning is a lookup.

Best agent combines both.

CodeRabbit Agent for Slack

Built for Agentic SDLC Workflows

Repositories
Repositories
482
Open PRs
83
Open PRs
Recent Changes
31
Recent Changes

Your org's operating context

The agent pulls your org's context together — across every tool and team conversation — into one place.

Built into the agent

A stylized diagram shows files connected to a central processing node.

Your agent’s skills

A stylized diagram shows files connected to a central processing node.

Automated workflows

A stylized diagram shows files connected to a central processing node.

Custom sandboxes

See how it works

How agent minutes work

Agent minutes measure active run time — the seconds an agent spends actually working on a task. We meter each run down to the second and sum it across your team for the billing period.

Agent minutes usage dashboard

FAQ

What is CodeRabbit Agent for Slack?

CodeRabbit Agent for Slack is built for agentic SDLC workflows. It pulls your org’s operating context together from across every tool and team conversation - code, tickets, docs, monitoring, cloud - and reasons over it to move work forward in the channel or thread where it’s already happening. It investigates, plans, opens PRs, captures team knowledge, and keeps everyone aligned as work evolves.

What is Agentic SDLC?

Agentic SDLC is a software delivery practice where AI agents participate meaningfully across the complete software development lifecycle - planning, requirement analysis, design, coding, testing, deployment, and maintenance. Instead of your team bouncing between point tools, the CodeRabbit Agent works alongside you, carrying context across phases, taking action on your behalf, capturing what the team learns, and staying accountable for its actions.

What Agentic SDLC actually needs?

To effectively implement the Agentic Software Development Lifecycle (SDLC), you need four key elements: a clear context of your organization's operations across code, issue trackers, and tools; a long-term, durable team knowledge; support for collaboration in existing communication channels; and proper governance with scoped access to tools and spend controls.

How to start using CodeRabbit Agent for Slack?

Sign in with Slack to establish the workspace identity. Then connect GitHub by linking your Slack workspace to the GitHub org. Install the CodeRabbit GitHub App to grant repository access. Optionally, you can edit the base scope - the default repositories, connections, and spend baseline for the workspace. Finally, start using CodeRabbit Agent for Slack, just mention @coderabbit in any channel or DM.

What tools does it integrate with?

CodeRabbit Agent for Slack connects with all the SDLC tools, such as Jira, Linear, Notion, Asana, Intercom, Zendesk, AWS, Datadog, CircleCI, PostHog, Sentry, PagerDuty, Figma, Canva, Google Drive, Gong, Pylon, OneDrive, and HubSpot. You can also plug in your own through MCP servers and APIs.

What are agent minutes, and how does pricing work for this product?

Agent minutes are the amount of active CodeRabbit runtime spent completing a task. The runtime measures elapsed sandbox time, from command start to run finish, and bills for minutes used.

Can I control what the CodeRabbit Agent can access?

Governance is integrated through scopes, which define everything the agent can do in a given context: accessible repositories, usable connections, user groups and users authorized to invoke it, and applicable spend limits. Every workspace starts with a default base scope, and additional scopes can be created that inherit from it and impose narrower restrictions.

How does knowledge base work with CodeRabbit Agent for Slack?

The knowledge base stores durable facts that it learned by working with your team. Knowledge respects Slack’s privacy boundaries, so public channels and shared surfaces use the global workspace knowledge base, private channels use a private conversation knowledge base, while DMs and group DMs use a private conversation knowledge base.

How can I monitor the usage of CodeRabbit Agent for Slack?

Just go to the Usage tab of your CodeRabbit Agent for Slack dashboard and monitor it from there.

Who can use and manage it?

CodeRabbit Agent for Slack responds only to workspace members. External users (guests) are blocked by default, and channels marked as externally shared are fully unsupported. For now, you can set up roles using the Workspace users section in your settings. Currently, you can pick between primary user, CodeRabbit admin, and scope admin (which requires a custom scope).

Where can I find more technical guidance regarding CodeRabbit Agent for Slack?

The most effective resource that will allow you to grasp all the technical concepts around CodeRabbit Agent for Slack would be our docs.

I already use CodeRabbit for code review. Is this the same thing?

Code review runs automatically on your pull requests. CodeRabbit Agent for Slack is built for agentic SDLC workflows. It lives in the channel or thread where your team already works, pulls your org’s operating context from across code, tickets, docs, monitoring, cloud, and reasons over it to investigate, plan, open PRs, and carry your team’s knowledge forward, all within guardrails you control. The two products share the same underlying engine.

Does this replace my engineers?

CodeRabbit Agent for Slack is designed to amplify your team, not replace it. It remembers what your team knows, handles the repeatable work, and surfaces context so engineers can focus on the hard decisions. Your team steers the agent in real time, reviews its work, and makes the calls that matter. The hard parts of engineering stay with the engineers.

Try it today

One agent for your entire Software Development Lifecycle. Right in Slack.

Try for free

Get $50/user free agent minutes.