AI has enabled teams to ship faster in 2025! 🤖 But incidents, postmortems, and a 1.7x higher bug rate in AI‑written code showed the side effects of AI augmented speed. In our new post, we detail how teams can make 2026 the year of AI quality! www.coderabbit.ai/blog/2025-w...

North Pole postmortem just released. Root cause: elves refactored the gift sorter “to make it more responsive,” introduced a textbook SQL injection, and one kid briefly qualified for 48,000+ presents. Mitigation: mandatory CodeRabbit on every PR. Full postmortem below.

Announcing "Share the Bug" CodeRabbit Holiday giveaway! 🗣️ To celebrate the end of a great year, we are giving away: > 1-year of individual CodeRabbit Pro > 1-year subscription of Frontend Masters > 1-year subscription to Egghead​.io To 10 people! Entry rules in the thread! 👇

Most AI dev tools obsess over vanity metrics like lines of code and accepted completions. The only metrics that matter: > What actually ships > Does it break production. Our new analytics dashboard puts this visibility directly into the hands of engineering leaders!

2025 was the year the internet kept breaking 🔥 🌐 Outages are up, incidents are up, and AI-generated code is a big part of the story! AI code now ships with around 1.7x more issues and more high‑risk vulnerabilities than human-written code.

Code review has quietly become a new bottleneck. AI helps devs ship more code which means more PRs, more risk, and less time to review carefully. So how about some AI Code Review to help with all the AI generated code? That's exactly what @coderabbitai.bsky.social built. expo.dev/blog/ai-powe...

AI coding assistants are shipping more code...but also more bugs! Our State of AI vs. Human Code Generation Report analyzed 470 real GitHub PRs. The findings? AI‑coauthored PRs produced about 1.7× more issues than human‑only PRs!

The CodeRabbit BLR team out in full force for the Microsoft AI Tour last Friday! A whole day of helping people learn to transform their orgs with the power of AI! 🇮🇳🐰

If anyone knows how challenging manual code reviews are, it’s The Linux Foundation. Before CodeRabbit, they dealt with: + Slow merge time + Hidden bugs + Low dev productivity Now, they’re sharing exactly why they love CodeRabbit in our case study. 👇

"Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it." - Brian Kernighan (co-creator of Unix) Is it even hard with AI involved? Let's talk about it 👇

The Vibe Code Cleanup Specialists have landed at AWS RE:Invent 2025! If you're suffering from dirty code, drop by the booth, chat to the team, and grab some clean merch 🤙🫧

Open source is booming, but so is maintainer burnout. Langflow turned to CodeRabbit to keep PR quality high, cut review bottlenecks, and make shipping faster (and saner) for their founder led team. Find out why Langflow loves CodeRabbit in our latest case study! 👇

If GPT-5.1 is the decisive teammate and Opus 4.5 the disciplined architect, Gemini 3 is the dense engineer who delivers a fully reasoned diff that is confident, comprehensive, and intent on proving its point.

The bottleneck in software development has shifted from writing code to validating it 🧪 84% of devs trust AI tools, but 48% still distrust the accuracy! Our latest blog post goes into all things AI code trust, and how we aim to solve it!

We benchmarked Opus 4.5 on coding tasks! We found it equals GPT 5.1 in many respects and is an improvement over Sonnet 4.5. If Sonnet 4.5 feels like a teacher and GPT-5.1 like a teammate, Opus 4.5 is the architect reviewing your PR!

CodeRabbit lets you connect multiple MCP servers for smarter code reviews! But why should you? > Enrich code reviews with context from multiple tools. > Make informed and precise reviews. Check out our latest blog to follow along and learn how to set up a Slack MCP server!

Introducing Agentic PR Summary! Need more from your CodeRabbit Summary? Now you can customize it with the new High Level Summary Instructions setting ✌️ > Auto fill your Pull Request Template. > Format it how you want: bullets, tables, sections. + Add custom instructions!

Shipping auth and user-management infra means zero tolerance for security lapses or spec violations. After adding CodeRabbit, Clerk managed to: + Cut time to merge by 40% + Catch 70% of edge-case bugs before human reviews Check out the full case study to see how they did it!

We are open-sourcing one of our internal tools! Introducing our AI-native open-source Git worktree manager CLI that works with all your AI Coding Agents ✌️ (that was a mouth full) Have fun!

The CodeRabbit team are getting ready for Microsoft Ignite next week! Catch us at booth 5314 🧽🧹

Looking for the best Microsoft Ignite after-party? We're hosting a social rooftop mixer with Anthropic on Wednesday, Nov 19th for AI engineers and leaders! Swing by the CodeRabbit HQ to enjoy a relaxed evening and raise to toast to the 1 year anniversary of MCP! 🥂

GPT-5.1 isn’t “GPT-5 but faster.” In our evals of the model, we found it’s the highest-precision model we’ve ever tested for code-related tasks like code review. Less noise, more fixes, reviews that read like patches again.

Our very own Director of AI, David Locker, will be taking to the stage at AI Dev 25 x NYC this Friday! He'll be talking all things CodeRabbit, Context Engineering & Prompt Engineering! 🐰🎙️

A CodeRabbit review per day, keeps the Merge Cop away!

The problem with 👍👎 is they optimize LLMs for approval, not truth. Stop training dev tools to chase treats like golden retrievers. Give high-signal, contextual feedback instead. Heres how!

Devs have always followed one core rule: faster is better. But AI isn’t magic. It’s inference. That's why engineering AI pipelines for accuracy, instead of low latency is crucial wherever correctness matters more than speed. Introducing... Slow AI. Move slow and fix things.

Theres still time to enter! 🗣️ ​> Hackathon Starts: October 29th > Submissions due: 12:00 PM PT on November 17th > Judging duration: November 17th to November 24th > Winners announced: November 24th Build a full-stack app and compete for $140k in cash prizes and credits! 💰

Attention Gemini lovers! 🔔 You can use CodeRabbit with Google’s Gemini CLI in a full agentic loop! Code with Gemini, review the changes with CodeRabbit, and fix the issues with Gemini.

CodeRabbit is proud to be mentioned in the NVIDIA GTC keynote as part of the AI startup ecosystem building on NVIDIA! Catch the full keynote from Jenson Huang below!

We’ve been named in the 2025 Disruptors 60 list! Curated by Greenfield Partners and live on TechCrunch this list names the most groundbreaking startups turning AI into real-world impact! Our mission is to scale code quality with AI, and this recognition validates that work!

CodeRabbit is now available on the Vercel Marketplace! > Works natively with Vercel projects. > 3‑step install from Marketplace. > Manage invoices and seat allocation directly from Vercel. Install link below!

If you're a funded startup looking to supercharge your engineering team, you can apply to our Startup Program! Get 50% off CodeRabbit Pro for 3 months. To be eligible, your startup must be: > VC- or accelerator-backed > Funded with $25 million or less

We kicked off day 1 of All Things Open the right way — a full evening of speed networking, real conversations, and a community that actually shows up. Huge shoutout to @digitalocean.com, @pomerium.io and @coderabbitai.bsky.social for making it happen.

Earlier this week, our CEO, Harjot Gill, took the stage at OpenAI's DevDay 2025 to showcase CodeRabbit. During the talk, Harjot discussed: > Second-order effects of Gen AI > Agentic verification within our analysis chain > Understanding PR intent based on repository context Full vid below 👇

Fancy rounding out SF Tech Week with some good vibes? Bring your board, borrow one, or just come for the coffee! We'll be unplugging after a long week of talks, talks, and more talks with some nice cold waves 🤙 See you there?

One trillion OpenAI tokens. One trillion tokens used to clean and ship quality code across the planet. We’re truly honored to receive this, it’ll take pride of place in our new SF office! 🧡🐇

100k GitHub installs? Completed it ✌️

If you're heading to @allthingsopen.bsky.social, come hang with the @digitalocean.com, @torc.dev, @coderabbitai.bsky.social and Pomerium crew on the 12th!

We benchmarked Claude Sonnet 4.5, and here is what we found! Sonnet 4.5 gets you close to Opus-level performance at a fraction of the price, making it a perfect sweet spot for teams. Here’s what’s new, surprising, and different👇

Our Director of AI and King of Pop Culture, David Loker was recently on the Super Data Science Podcast! He covered: > CodeRabbit (Of course) > Context Engineering > Data security at CodeRabbit > Vibe Coding You can check out the full 1hr 17 episode in the thread below!

Find bugs, Fix bugs!

Catch AI slop before it ships. 🔥 The new @coderabbitai CLI brings senior-level AI code review directly to your terminal. Code reviews are essential for shipping quality products, but let's face it: nobody wants to sift through them just to spot typos. Enter: CodeRabbit! 👇

After rolling out GPT-5 within CodeRabbit, we (and you) noticed reviews became too pedantic, dropping the signal-to-noise ratio. The release of GPT‑5 Codex, plus the product changes we made, brings our ratio back home without sacrificing the ability to find the hard bugs! 🧵

🎉 Introducing Agentic Pre-Merge Checks! 🔎 Use built-in checks for common use cases, or add your own custom checks tailored to your team’s policies! > Run sandboxed shell commands > Consult public documentation > Call connected MCP tools What workflows will you discover?

Best merch on #dcbln25 from @coderabbitai.bsky.social

You can now enable Codex to execute CodeRabbit directly in your development workflow! Let AI code, review, and fix issues autonomously without any human intervention 🤖 (Check out the updated CodeRabbit CLI x Codex docs below!)

Today, we’re proud to announce a $1 million USD commitment to open source software sponsorships! 🎉 This commitment reflects both our gratitude for what open source makes possible and our belief in the importance of investing in its future! 🙏

Introducing CodeRabbit CLI! 🎉 CodeRabbit's smart CLI reviews act as quality gates for Codex, Claude, Gemini, and you. Stop shipping slop. Start shipping quality.

We’re excited to announce that we've raised a $60M Series B to help teams focus on building and shipping with AI instead of endlessly reviewing! This round was led by Scale Venture Partners, with participation by NVentures (NVIDIA's venture capital arm).