Skip to main content

· 6 min read
Pradeep Sharma

The 'modern AI stack for developer productivity' refers to a comprehensive set of AI-powered developer tools that improve developer productivity in building software. In 2023, Large Language Models (LLMs) caused significant disruption, leading to a rapid increase in the adoption of artificial intelligence within the development lifecycle, particularly in the realm of 'developer productivity tools'. A significant majority of software development projects are now leveraging some form of AI, specifically Generative AI to transform traditional development workflows into more intelligent, efficient, and automated processes.

The modern AI stack for developer productivity is reshaping the landscape of software development, making tasks that were once time-consuming or complex more manageable and automated. From helping with the research or code writing to reviewing code and ensuring quality, the modern AI stack is a testament to how AI is not just an add-on but an integral component in the software development process.

Are you leveraging the full potential of the modern AI tech stack in your projects? This article might help you to get that perspective needed to understand how it might elevate your work to the next level.

· 7 min read
Gur Singh

Since its inception, CodeRabbit has experienced steady growth in its user base, comprising developers and organizations. Installed on thousands of repositories, CodeRabbit reviews several thousand pull requests (PRs) daily. We have previously discussed our use of an innovative client-side request prioritization technique to navigate OpenAI rate limits. In this blog post, we will explore how we manage to deliver continuous, in-depth code analysis cost-effectively, while also providing a robust, free plan to open source projects.

· 8 min read


Welcome to the future, where morning commutes involve going from bed to home office. The dress code is "business on top, pajamas down below." In this new world of remote work, tech teams worldwide are getting good at video calls and wishing for strong Wi-Fi like strong coffee. But here's the question: How do we maintain engineering efficiency when Joe from frontend is in Mexico, and DevOps Dave just started his day in Dublin? This setup presents a unique challenge: ensuring that code reviews, which are essential for code quality, are consistent, timely, and efficient. Have you ever missed a code review because it was late at night? We've all been there. Are you waiting for days to get feedback because your reviewer is in a different time zone? Oh, the frustration! Introducing the helpful algorithm: AI-driven code reviews. They're like a reliable friend who never sleeps (because they're code) and knows all the coding rules. This article explores how these intelligent bots fill the gaps in our fast-paced, sometimes slow, new world.

· 12 min read
Gur Singh
Suman Kumar
Nato Boram

Since CodeRabbit launched a couple of months ago, it has received an enthusiastic response and hundreds of sign-ups. CodeRabbit has been installed in over 1300 GitHub organizations and typically reviews more than 2000 pull requests per day. Furthermore, the usage continues to flourish; we are experiencing a healthy week-over-week growth.

While this rapid growth is encouraging, we've encountered challenges with OpenAI's stringent rate limits, particularly for the newer gpt-4 model that powers CodeRabbit. In this blog post, we will delve into the details of OpenAI rate limits and explain how we leveraged the FluxNinja's Aperture load management platform to ensure a reliable experience as we continue to grow our user base.

· 12 min read
Simone Cuomo


In the era of building and improving products fast, engineering managers encounter fresh challenges that render traditional strategies outdated. The amount of time spent trying to make sure that teams not only build products fast, but also without breaking too much stuff or introducing security vulnerabilities is significant.

One of the most time-intensive tasks involves conducting code reviews – these crucial checkpoints serve as guardians shielding your codebase from potential chaos. Additionally, code reviews are an essential part of compliance; which is often a requirement when working in an enterprise. Despite their significance, they can also turn into obstacles, occasionally stalling the deployment process. The question at hand is: How can we navigate through this impediment while upholding top-notch code quality?

Introducing AI-powered code reviews! Picture your team's pull requests getting reviewed as soon as they're made. That's the magic of AI code review tools. For teams, this means you don't have to wait for hours to get feedback. Reviewers can still offer more feedback later. It also means your teams can stay on track, creating and releasing features without the usual delays of waiting for code reviews.

We'll discuss the regular stages of software projects and the impact of AI code reviewers like CodeRabbit in this digital era. You'll gain a detailed insight into how these tools are changing the game, making code reviews faster, smarter, and surprisingly, more human-like.

· 10 min read
Gur Singh
Vishu Kaur

We are witnessing an inflection point in the software development industry. Developers around the world have been realizing the incredible possibilities that AI can bring. The introduction of GitHub Copilot and ChatGPT have revolutionized software development. They have been the fastest-growing tools in the history of software development.

While on the code generation side, many tools have emerged, the code review process has remained largely unchanged. We continue to use the same tools and processes that were used 10 years ago. The code is still manually reviewed, which is slow, error-prone, and expensive. To address this, we are building CodeRabbit, an AI-powered code reviewer that is part of the code merge and CI/CD process. With CodeRabbit our vision is to speed up the code merge process by an order of magnitude, while also improving the quality of the code that goes beyond what is possible with human reviewers alone and existing linting tools.