Skip to content

All articles — Page 9

Your AI agent has amnesia

Your AI agent has amnesia

Fifty years of SDLC evolution pushed engineering toward shared understanding. Coding agents reversed the trend in 18 months.

04.22.26
Measure twice, cut once: How CodeRabbit built a planning layer on Claude

Measure twice, cut once: How CodeRabbit built a planning layer on Claude

CodeRabbit's planning layer is built on Claude to catch costly assumptions before coding begins, helping teams ship better, more reliable AI-generated code, faster.

04.21.26
What Claude Opus 4.7 means for AI code review

What Claude Opus 4.7 means for AI code review

Claude Opus 4.7 outperformed in 100 evaluations across real open-source pull requests—finding more real bugs, delivering more actionable feedback, and reasoning across files better than anything we’ve tested.

04.16.26
Introducing the CodeRabbit plugin for Codex

Introducing the CodeRabbit plugin for Codex

Get AI-powered code reviews without leaving Codex. The CodeRabbit plugin runs reviews inside your session, catches bugs before PRs, and requires zero workflow changes to set up.

04.15.26
Our settings page was overwhelming our users. Here's what we did to fix it

Our settings page was overwhelming our users. Here's what we did to fix it

our settings page became a wall of options that overwhelmed a lot of users. Here's how we solved it and what we learned along the way.

04.10.26
Your plan has a limit. Your sprint doesn't have to.

Your plan has a limit. Your sprint doesn't have to.

The PR Usage-based Add-on lets your team keep reviewing PRs even after hitting a subscription limit - without upgrading your plan, manual intervention or per-reviewer setup. Once enabled through CodeRabbit dashboard, the rabbit automatically continues processing PR reviews beyond the limit, billing only the over-limit usage as pay-per-use. Credits kick in after the limit is reached, not before. Your regular usage stays on your plan. Only the overflow gets charged.

04.09.26
You don’t need to implement that. Autofix will.

You don’t need to implement that. Autofix will.

You open a pull request. CodeRabbit reviews it and leaves a handful of comments. So now you do what every developer does: Read each comment, Context-switch back into the code, Make the fix, Push a n...

04.02.26
A very brief history of AI coding, from Copilot to next-gen agents

A very brief history of AI coding, from Copilot to next-gen agents

How code models became coding assistants, how assistants became agents, and how the practice of software engineering began to reorganize around them.

03.18.26
Meet CodeRabbit Plan: better plans. Faster delivery. Less rework

Meet CodeRabbit Plan: better plans. Faster delivery. Less rework

The challenge Teams using coding agents need prompts that are clear, specific and context-aware. That's exactly why we built CodeRabbit Plan, a collaborative planning tool that turns vague ideas into

03.18.26