David Kravets

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Go into a project without a plan and you'll spend more time fighting problems than building. Here's the story of how we built a planning layer on Claude to fix that. 👇

We’re adding more plugins to Codex to give it more ways to gather context and take action across your stack. New plugins include @coderabbitai, @Remotion, @CircleCI, and more.

We ran Anthropic Claude Opus 4.7 against our hardest benchmark - complex concurrency bugs that require multi-step reasoning. Almost 20% better than previous generations. Here's what we did to get it production-ready and what you can take from it for your own stack 👇

CodeRabbit is now a Codex plugin. Review your code without leaving the agent. Ask, get findings by severity, fix, ship.

The faster your engineers ship with AI, the more code review becomes the bottleneck! freee saw it coming before it became a crisis 🚨 > 54% acceptance rate on critical issues > 32.8 weeks of reviewer time saved > Reduced manual code-review burden → coderabbit.ai/case-studies/h…

Most founders don’t understand open source when starting their OSS business. I went deep with @ivanburazin on the full @daytonaio journey - how they build a product that tops benchmarks against Vercel, solves the critical bottleneck for AI agents and drives crazy adoption...

Open Source Models you have been sleeping on! x.com/i/broadcasts/1…

It’s simple to give your agent access to CodeRabbit as a tool to perform code reviews. we shipped improvements in the output to make it easier for agents to consume the findings and fix the issues for you.

wild to see how far hackers are willing to go to perform supply chain attacks.

How do you scale an open-source project to over a million downloads a day? 🤔 We sit down with Bill Easton, core maintainer of FastMCP and Director of Product at Elastic, to dive deep into the Model Context Protocol (MCP) ecosystem. Full video in the comments! 👇

Apple's been struggling to fix Siri for years. Google just dropped Gemma 4. It's open-source (Apache 2.0), runs fully on-device, offline, near-zero latency, multimodal audio/video, agentic multi-step workflows and engineered to preserve RAM and battery on phones. That's not just a dev tool. That's a Siri brain waiting to be licensed. Just sayin'. #AI #Siri #Gemma4 blog.google/innovation-and…

CodeRabbit already tells you what to fix. Now it fixes it too. @​coderabbitai autofix All unresolved findings, implemented. Commit to your branch or open a stacked PR.

Thank you Jensen and NVIDIA! She’s a real beauty! I was told I’d be getting a secret gift, with a hint that it requires 20 amps. (So I knew it had to be good). She’ll make for a beautiful, spacious home for my Dobby the House Elf claw, among lots of other tinkering, thank you!!

Introducing CodeRabbit Plan. Hand those prompts to whatever coding agent you use and start building!

Miss all the fun at GTC this year, but what we are cooking might just be worth the FOMO. Stay tuned!