Skip to content

All articles — Page 16

How CodeRabbit delivers accurate AI code reviews on massive codebases

How CodeRabbit delivers accurate AI code reviews on massive codebases

Massive codebases are a special kind of beast. They sprawl across hundreds of files, evolve over years of commits, and occasionally feel like they’re held together by equal parts duct tape and institutional memory. Reviewing changes in that environme...

09.05.25
We asked CodeRabbit to talk to us like your disappointed mom & it did!

We asked CodeRabbit to talk to us like your disappointed mom & it did!

Have you truly lived before an AI reviewer has told you, “I ran this locally and my laptop filed for workers’ comp?” We doubt it. Welcome to CodeRabbit’s Tone Customization, a feature we added because we know exactly what developers want most: to be ...

08.28.25
Our response to the January 2025 Kudelski Security vulnerability disclosure: action and continuous improvement

Our response to the January 2025 Kudelski Security vulnerability disclosure: action and continuous improvement

No customer data was accessed and the vulnerability was quickly remediated within hours of disclosure

08.19.25
Vibe coding: because who doesn’t love surprise technical debt!?

Vibe coding: because who doesn’t love surprise technical debt!?

AI-assisted coding tools like Claude Code, ChatGPT, and GitHub Copilot are a godsend. I use them every day — for boilerplate, bug fixes, fast explorations, even documentation. I'm all in on AI as a productivity booster and creative accelerator. But t...

08.14.25
Benchmarking GPT-5: Why it’s a generational leap in reasoning

Benchmarking GPT-5: Why it’s a generational leap in reasoning

The wait is over! As the leading AI code review tool, CodeRabbit was given early access to OpenAI’s GPT-5 model to evaluate the LLM’s ability to understand, reason through, and find errors in complex codebases. As part of our GPT-5 testing, we've con...

08.07.25
GitHub Copilot best practices: 10 tips & tricks that actually help

GitHub Copilot best practices: 10 tips & tricks that actually help

Copilot has quickly become a staple in the modern developer’s toolkit. Powered by OpenAI’s models, it offers AI-driven code suggestions based on what you’re writing — right in your editor. Used well, it can significantly boost productivity. Microsoft...

07.23.25
Context engineering: level up your AI code reviews

Context engineering: level up your AI code reviews

Context is everything – especially in code reviews At CodeRabbit, we have engineered the most context-rich code reviews in the industry. While other code review tools might skim the surface and settle for just “codebase awareness,” we go deeper. We p...

07.17.25
The art and science of context engineering for AI code reviews

The art and science of context engineering for AI code reviews

The difference between a mediocre and exceptional AI agent comes down to one thing: context. Context engineering has recently become a buzzword. In late June, Shopify CEO Tobi Lutke tweeted about it and Andrej Karpathy chimed in to point out that goo...

07.16.25
What percentage of your code should be AI-generated?

What percentage of your code should be AI-generated?

We’ll come clean: That title is mostly clickbait. This isn’t an article where we tell you that 20% or 30% or even 50% of your codebase should be AI-generated. We’re writing this because it’s looking like very soon someone could be telling you that. M...

07.08.25