llms.txt
# CodeRabbit
> AI-driven code now outpaces human capacity. We help teams ship code, not surprises.
This index is generated from CodeRabbit's Git-owned English website content. Verify setup and product behavior against the linked page and official documentation.
## Product
- [The future isn't writing code. It's understanding it.](https://www.coderabbit.ai): AI-driven code now outpaces human capacity. We help teams ship code, not surprises.
- [One agent for your entire Software Development Lifecycle. Right in Slack.](https://www.coderabbit.ai/agent): Bring the agentic SDLC into Slack with CodeRabbit, where teams can plan work, answer repo questions, and keep development moving.
- [Vibe check your Code, now in CLI](https://www.coderabbit.ai/cli): Smart CLI Reviews act as quality gates for Codex, Claude, Gemini, and you.
- [CodeRabbit Plan | Structured Plans for AI Coding](https://www.coderabbit.ai/plan): Turn vague ideas into structured plans and context-rich prompts
- [Vibe check your code](https://www.coderabbit.ai/ide): Free AI code reviews directly in the IDE. Ship faster while maintaining your flow state.
- [Quality gates for every PR](https://www.coderabbit.ai/enterprise): Your org standards. Enforced on every PR, across every team.
- [CodeRabbit Pricing](https://www.coderabbit.ai/pricing): CodeRabbit offers the most comprehensive set of tools to help you ship code you trust, with plans to suit any engineering team.
## Learning hubs
- [CodeRabbit Blog](https://www.coderabbit.ai/blog): Dig into insights about our products, use cases, and POVs
- [Agentic Learning Center](https://www.coderabbit.ai/guides): Explore CodeRabbit guides on agentic SDLC, AI code review, coding agents, code explainability, Slack workflows, and governance for AI-assisted engineering teams.
- [Case Studies](https://www.coderabbit.ai/case-studies): See how engineering teams use CodeRabbit to reduce review time, catch critical issues, and improve code quality across real-world projects.
- [Reports & Guides](https://www.coderabbit.ai/whitepapers): Browse CodeRabbit reports and guides on AI code review, agentic development, security, code quality, and modern engineering workflows.
## Guides
- [Adopt agentic engineering without losing your review loop](https://www.coderabbit.ai/guides/agentic-engineering): Agentic engineering typically breaks in the review queue. In this piece we go over risk-tier reviews, adding an independent first pass, and tracking the metrics that hold.
- [AI agent governance: A framework for engineering leaders](https://www.coderabbit.ai/guides/ai-agent-governance): Set permissions, review gates, audit trails, and human approval rules for coding agents across the software development lifecycle.
- [AI explainability is a security requirement: why opaque PRs are a risk](https://www.coderabbit.ai/guides/ai-explainability-is-a-security-requirement): Opaque AI-generated PRs ship code nobody fully understands. Learn why explainability belongs in your security model, and what to require before merge.
- [AI governance for coding agents: policies and enforcement](https://www.coderabbit.ai/guides/ai-governance-coding-agents): Configure coding-agent permissions, repository policies, review gates, and audit evidence, with a practical workflow for handling exceptions.
- [AI pair programming in the agentic SDLC: When review becomes the bottleneck](https://www.coderabbit.ai/guides/ai-pair-programming): AI pair programming inverts the roles. The agent writes the code and you review it, and at agent throughput review becomes the bottleneck. Here's how to keep up.
- [AI security code review: Improve code security before merge](https://www.coderabbit.ai/guides/ai-security-code-review): AI security code review helps teams inspect risky pull-request changes, explain code security findings, and improve security before merge.
- [Bring agentic code review to your existing PR workflow](https://www.coderabbit.ai/guides/agentic-code-review): Learn how agentic code review checks a pull request, uses repository context, and fits into your existing review and merge workflow.
- [Build an AI second brain for engineering teams](https://www.coderabbit.ai/guides/ai-second-brain-for-engineering): An AI second brain for engineering teams captures codebase decisions and review history, then applies them at review time so knowledge stays when they leave.
- [Build vs. buy a Slack agent: A decision framework](https://www.coderabbit.ai/guides/build-vs-buy-slack-agent): Once a Slack agent can merge code, the real cost is verification, not tokens. A build-vs-buy framework for engineering leaders deciding how to ship one.
- [Building a quality gate that works for AI-generated code](https://www.coderabbit.ai/guides/ai-generated-code-quality-gate): Learn how to build a credible quality gate for AI-generated code using independence, agnosticism, discernment, and explainability.
- [Code context: The evidence behind trustworthy AI code review](https://www.coderabbit.ai/guides/code-context): Code context is the evidence an AI reviewer sees beyond the diff. Here's why deep context, not a bigger window, makes AI code review trustworthy.
- [Code explainability for AI-generated PRs: A reviewer's guide](https://www.coderabbit.ai/guides/code-explainability-for-ai-generated-prs-a-reviewers-guide): When an agent writes the PR, 'ask the author' stops being a reliable review tool. Use this practical workflow to review intent, blast radius, error paths, and evidence before merge.
- [Code review best practices for AI-generated code](https://www.coderabbit.ai/guides/code-review-best-practices-for-ai-generated-code): AI-generated diffs require updated review practices. Best practices focus on establishing intent, following dependency order, and managing volume in the agentic era.
- [Collaborative AI: repo rules, tickets, and review history for the agentic SDLC](https://www.coderabbit.ai/guides/collaborative-ai-for-agentic-sdlc): Collaborative AI keeps humans and agents working from shared repo rules, tickets, and review history so teams can trust and build on AI-generated code.
- [How technical debt compounds faster when AI writes the code](https://www.coderabbit.ai/guides/how-technical-debt-compounds-faster-when-ai-writes-the-code): Learn why technical debt can compound faster with AI-generated code and how independent verification, shared understanding, and documented decisions help.
- [How to build a Slack bot that reviews your code](https://www.coderabbit.ai/guides/how-to-build-slack-bot-code-reviews): Learn three practical ways to bring code review into Slack, from GitHub notifications to a custom Slack bot and CodeRabbit Agent for Slack.
- [How to build an AI coding agent (and when not to)](https://www.coderabbit.ai/guides/how-to-build-an-ai-coding-agent): The hard part of building an AI coding agent isn't the loop or the tools. It's knowing when not to build one, and what breaks once it starts shipping code.
- [How to design agentic workflows that actually ship](https://www.coderabbit.ai/guides/how-to-design-agentic-workflows): Agentic workflows ship reliably only when an independent verification step gates the merge. How to design that gate, instrument the risk, and keep accountability with a human.
- [How to get AI code review alerts in Slack](https://www.coderabbit.ai/guides/ai-code-review-alerts-slack): Compare four ways to route AI code review alerts into Slack without turning review channels into noisy notification feeds.
- [How to keep AI code review consistent across coding agents](https://www.coderabbit.ai/guides/consistent-ai-code-review-across-coding-agents): Learn how to keep one review standard across Codex, Claude Code, Cursor, other coding agents, and human-written pull requests.
- [PR summaries vs. PR explainability: Closing comprehension debt](https://www.coderabbit.ai/guides/pr-summary-vs-pr-explainability): Green pull requests can still ship bugs when summaries replace true comprehension. Explainable review interfaces help teams restore system understanding.
- [SAST vs SCA: Why neither is enough](https://www.coderabbit.ai/guides/sast-vs-sca-why-neither-is-enough): Compare SAST and SCA, understand their strengths and limits, and learn why application context matters for authorization and business-logic security.
- [Static analysis vs. AI code review: Which catches what?](https://www.coderabbit.ai/guides/static-analysis-vs-ai-code-review): Static analysis checks rules and program models. AI code review adds context. Learn what each catches, where coverage overlaps, and how to use both.
- [The agentic software development lifecycle: How AI agents are reshaping every phase](https://www.coderabbit.ai/guides/agentic-sdlc): The agentic SDLC puts AI agents at every phase of software development. See how it reshapes planning, dev, review, and what teams need to ship safely.
- [The engineer's guide to a coding agent workflow](https://www.coderabbit.ai/guides/coding-agent-workflow): A coding agent workflow runs the loop from plan to merge with AI agents in it. The generation-to-verification boundary is what controls the risk.
- [The guide to guardrails for agentic coding workflows](https://www.coderabbit.ai/guides/guardrails-for-agentic-coding-workflows): Learn how feed-forward and feedback guardrails catch AI agent errors, enforce standards, and keep unsafe code from reaching production.
- [The practical guide to agentic context engineering](https://www.coderabbit.ai/guides/agentic-context-engineering): Agentic context engineering decides whether your AI code review agent catches the bug or lets it ship. Here's how to get the context right.
- [Types of AI coding agents (and where each fits in your workflow)](https://www.coderabbit.ai/guides/types-of-ai-coding-agents): A practical guide to the six types of AI coding agents (IDE, CLI, background, review, planning, and Slack-native) and where each fits in your development workflow
- [What are Slack agentic workflows? How they work and how to use them](https://www.coderabbit.ai/guides/slack-agentic-workflow): Slack agentic workflows let AI agents open PRs, triage incidents, and run standups where your team works. Here's how they work and where to start.
- [What does “LGTM” mean in code review, and when is it a warning sign?](https://www.coderabbit.ai/guides/what-does-lgtm-mean-in-code-review-and-when-is-it-a-warning-sign): Learn what LGTM means in code review, why large pull requests can receive shallow approvals, and how better review interfaces improve understanding.
- [What does an agentic SDLC actually look like end-to-end?](https://www.coderabbit.ai/guides/agentic-sdlc-end-to-end): See what an agentic SDLC looks like across planning, code generation, review, testing, deployment, and operations.
- [What Is Agentic Change Management?](https://www.coderabbit.ai/guides/what-is-agentic-change-management): Agentic Change Management governs software changes from proposal through post-merge maintenance when humans and AI agents both produce code.
- [What is agentic coding? Workflow, examples, and review](https://www.coderabbit.ai/guides/what-is-agentic-coding): Learn how agentic coding works, how it differs from AI-assisted and vibe coding, and where testing and independent code review fit into the workflow.
- [What is AI agent explainability? A 2026 SDLC primer](https://www.coderabbit.ai/guides/ai-agent-explainability): AI agent explainability lets engineering leaders trace every AI agent decision in the SDLC to a rule, policy, and diff. Learn what it means.
- [What is AI code governance?](https://www.coderabbit.ai/guides/what-is-ai-code-governance): AI code governance is how teams keep AI-written code trustworthy without slowing developers down. Learn what it includes and how it works in practice.
- [What is code review, and how is it changing?](https://www.coderabbit.ai/guides/what-is-code-review-and-how-is-it-changing): Code review is the decision about whether a change is safe to ship, made by someone other than the author. Learn how AI is changing that checkpoint.
- [What is context engineering? A primer for AI-assisted teams](https://www.coderabbit.ai/guides/what-is-context-engineering): Context engineering gives AI agents the right information and structure. For teams shipping production code, it's what makes review trustworthy.
- [What is harness engineering for AI code review without losing oversight?](https://www.coderabbit.ai/guides/harness-engineering-ai): Harness engineering for AI centers on four rings. The part most teams skip is verification. Here's how to close it.
- [What is self-healing code? And how close we actually are](https://www.coderabbit.ai/guides/self-healing-code): Self-healing code promises autonomous bug repair, but the gap between hype and reality is real. Here's what works in production today and what doesn't.
- [Why explainability is the new observability layer for pull requests in the agentic SDLC](https://www.coderabbit.ai/guides/pull-request-explainability-agentic-sdlc): Learn why large agent-generated pull requests need explainability, not just file-by-file diffs, so reviewers can understand change intent before merge.
## Customer stories
- [Buy vs build: Why WRITER bought their AI code review tool](https://www.coderabbit.ai/case-studies/buy-vs-build-why-writer-bought-their-ai-code-review-tool): Learn why WRITER decided to buy instead of build their AI code review tool and how it shaved 30% off their review time.
- [EarnIn scales regulated code review with CodeRabbit after choosing buy over build](https://www.coderabbit.ai/case-studies/earnin-scales-regulated-code-review-with-coderabbit-after-choosing-buy-over-build): See how EarnIn uses CodeRabbit across hundreds of GitHub repositories to review 5,000+ PRs, save 12 weeks of reviewer effort, and govern AI-assisted development.
- [How Abnormal AI scales autonomous development with CodeRabbit](https://www.coderabbit.ai/case-studies/how-abnormal-ai-scales-autonomous-development-with-coderabbit): CodeRabbit became the enforcement layer across both AI and human-written code, catching subtle security and correctness issues static tools miss. With a 65%+ acceptance rate on critical findings and 100+ hours saved per month, Abnormal…
- [How Briya uses CodeRabbit to govern every AI coding agent](https://www.coderabbit.ai/case-studies/how-briya-uses-coderabbit-to-govern-every-ai-coding-agent): See how Briya uses CodeRabbit Learnings, multi-repo context, and Linear MCP checks to govern AI-generated code with about 60% suggestion acceptance.
- [How Cadent uses CodeRabbit to scale AI-assisted development and align engineering teams](https://www.coderabbit.ai/case-studies/how-cadent-scales-ai-assisted-development-with-coderabbit): CodeRabbit helps Cadent accelerate code review, catch defects before they reach production, and extend shared engineering standards across a growing organization.
- [How Capacity solved the AI code review bottleneck](https://www.coderabbit.ai/case-studies/capacity-saves-five-weeks-of-developer-review-time-with-coderabbit): See how Capacity uses CodeRabbit to automate first-pass review and keep human attention on judgment calls.
- [How CloudTalk built CodeRabbit into its multi-agent development workflow](https://www.coderabbit.ai/case-studies/how-cloudtalk-built-coderabbit-into-its-multi-agent-development-workflow): CloudTalk brings local checks and pull request feedback into the work of its internal coding agents, before a developer reviews the result.
- [How CodeRabbit helped Plane get their release schedule back on track](https://www.coderabbit.ai/case-studies/how-codeRabbit-helped-plane-get-their-release-schedule-back-on-track): See how Plane used CodeRabbit to shorten review cycles, reduce production bugs, and unblock releases across its cloud, self-hosted, and open-source products.
- [How CodeRabbit helped The Linux Foundation streamline code reviews and accelerate development](https://www.coderabbit.ai/case-studies/how-coderabbit-helped-the-linux-foundation-streamline-code-reviews-and-accelerate-development): The Linux Foundation was experiencing slow manual code reviews that was leading to code review bottlenecks. Learn how they ended long review cycles.
- [How CodeRabbit is helping Swiggy ship faster](https://www.coderabbit.ai/case-studies/how-coderabbit-is-helping-swiggy-ship-faster): See how Swiggy cut merge time by 70%, flagged thousands of issues early, and reduced review cycles by 30% using CodeRabbit across Java, Go, Node, Python, Kotlin, PHP, Scala, and Android native.
- [How Common App cut code review time by 35% & found more bugs](https://www.coderabbit.ai/case-studies/how-common-app-cut-code-review-time-by-35-percent-and-found-more-bugs): Reduced code review time by 35%, eliminated the need for two reviewers, and helped prevent security vulnerabilities.
- [How Cresta brings consistent review to AI-generated code with CodeRabbit](https://www.coderabbit.ai/case-studies/how-cresta-brings-consistent-review-to-ai-generated-code-with-coderabbit): Cresta’s Technical Lead Manager Jianan Xing says the company gets “more value than what we pay” as teams use CodeRabbit to catch bugs, check compatibility, and apply engineering standards.
- [How freee saved months of reviewer time with CodeRabbit](https://www.coderabbit.ai/case-studies/how-freee-saved-months-of-reviewer-time-coderabbit): Learn how freee saved months of code-reviewer time across a large developer footprint, and improved review quality and generally reduced the workflow burden on engineers with CodeRabbit.
- [How LeoLabs scales Orbital Intelligence with CodeRabbit](https://www.coderabbit.ai/case-studies/how-leolabs-scales-orbital-intelligence-with-coderabbit): See how LeoLabs uses CodeRabbit to find latent bugs, reduce cross-repository false positives, and meet strict defense governance requirements.
- [How NetSPI brings code quality back in line with AI-driven throughput with CodeRabbit](https://www.coderabbit.ai/case-studies/how-netspi-brings-code-quality-back-in-line-with-ai-driven-throughput-with-coderabbit): NetSPI restores code quality at AI-driven throughput with CodeRabbit, reviewing 517 pull requests across 42 repositories in a recent 90-day period.
- [How Nursa rebuilt its platform in 7 months without losing quality with CodeRabbit](https://www.coderabbit.ai/case-studies/how-nursa-rebuilt-its-platform-in-7-months-without-losing-quality): See how Nursa rebuilt seven years of product in seven months and used CodeRabbit to verify AI-generated code, catch sensitive-data risks, and ship continuously.
- [How Prokeep catches breaking changes and prepares to scale AI code review with CodeRabbit](https://www.coderabbit.ai/case-studies/how-prokeep-catches-breaking-changes-and-scales-ai-code-review-with-coderabbit): Learn how Prokeep uses CodeRabbit to catch risky database migrations, find functional edge cases, and scale AI-assisted development without sacrificing code quality.
- [How SalesRabbit reduced bugs by 30% and increased velocity by 25%](https://www.coderabbit.ai/case-studies/how-salesrabbit-reduced-bugs-by-30-and-increased-velocity-by-25): Learn how SalesRabbit used CodeRabbit to improve engineering productivity, reduce bugs, and create consistency across a complex, multi-language codebase.
- [How Showpad slashed code review time 65% with CodeRabbit](https://www.coderabbit.ai/case-studies/how-showpad-slashed-code-review-time-65-percent-with-coderabbit): When Showpad let engineers pick their own AI tools, they chose CodeRabbit. Review workload dropped 65% and onboarding got 2.3× faster.
- [How Visma enhanced code quality and streamlined reviews](https://www.coderabbit.ai/case-studies/how-visma-found-the-enhance-code-quality-and-streamline-reviews): Visma needed a code review AI for large codebases to help them deal with complex interdependencies in their legacy code.
- [Inside Clerk’s 40% faster merge workflow with CodeRabbit](https://ww
