Building the future of code review @CodeRabbitAI Host of The Merge, Founder https://xitter.twitterapi.xyz/t.co/PrQJ9avJtj Sharing what I learn from founders, engineers, and open-source builders
San Francisco, CA
Joined January 2025
- Tweets831
- Following540
- Followers728
- Likes1.5K
Pinned Tweet
We've merged 5845 PR's into prod last week alone at Coderabbit...
It's kinda hard to keep up, even from the inside, so I went on a short walk to get you up to speed:
Here is what's new
Hendrik Krack retweeted
CodeRabbit is now in Antigravity's Plugin marketplace 🐰
Your agent writes the code and CodeRabbit reviews it in the same workflow, before anything ships!
Hendrik Krack retweeted
We've increased CodeRabbit's engineering output roughly 20x in six months with the same sized engineering team. Marketing, sales, ops. All need to move at the same speed.
We're turning how we run the company into resources agents can read and work with:
• Agents launch and update campaigns, with changes reviewed before they go live.
• Codex builds slide decks and customer documents in our content studio.
• CodeRabbit Slack bot investigates incidents and support tickets, then proposes fixes as PRs.
We're moving more of the company's knowledge and workflows out of documents and into code. Plans, processes, and content become things agents can act on, with changes we can review and track.
Faster code isn't enough. The whole business has to keep up. I spoke with @OpenAI about the workflows we rebuilt and the bottlenecks we had to fix.
Full story below.
RT @harjotsgill: Coderabbit's Secure free Deep Scan wrap-up:
- 13K+ scans, 2.7K+ orgs
- 550K+ unique code-security findings
- 40K+ critical…
Hendrik Krack retweeted
We put GPT-6 Cyber inside CodeRabbit’s security scan pipeline.
22 of 33 known vulnerabilities caught vs 19 for our production ensemble, and 66% more high and medium severity findings.
Full eval below.
Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment.
The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work.
GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time.
openai.com/index/introducing…
There is really not that much moat left in engineering for many good ideas.
not saying this generalizes to all but execution speed & large distribution will dominate the years to come
I recreated subvocal in 9 minutes with one prompt for AirPods Pro 3.
Source: github.com/joeblau/subvox
6
381
Really stoked about our collaboration with @antigravity, with much more to come soon!
Shout out to @ckbrox13 👀
Another great sunset event on our @coderabbitai rooftop 🌆
Follow our luma calendar and join us for the next one!
luma.com/coderabbitai
All software as we know it is under an immense threat right now.
Proud to be working at a company with so many talented people making the internet a safe place again.
Kudos to our team & to our founders who have pledged $1M in credits for folks to upgrade their security.
Great vibes and even better tea 🫖
Here’s what I took away:
• @romainhuet and the DevEx team shared their thinking on “What Comes After Loops?”
One practical detail from the slides: keep a worklog of the goal, current instructions, who owns what, unfinished work and decisions. When instructions change, reconcile them with work already underway. After a context compaction or handoff, read the log and check the actual state before continuing.
That gives an agent something concrete to pick up from when the work spans multiple sessions.
• @dkundel made a great argument for defaulting to one agent session before building overcomplicated orchestration.
Most tasks can be handled perfectly well in one Codex thread. Give it responsibility for the outcome and let it delegate independent work where that helps.
The “Coordinate” and “Manager” skills shown on stage made this concrete: split work with clear ownership, let agents resolve dependencies directly, and name someone to assemble and check the result. If two agents are working together, define which parts each can edit and use cloud env so they don’t overwrite each other’s work locally.
Also, avoid creating too many org layers and therefore managerial debt
• @whoiskatrin talked about what it would take to keep Codex running for 10,000 hours straight.
The “keep CI green” example made this tangible. The accompanying AGENTS.md told the agent to run the failing test before and after a fix, keep notes in ci-notes.md, and open a PR explaining what it tested.
It also set clear boundaries: don’t disable tests to make CI pass, don’t trigger unnecessarily large CI runs, and leave the PR for review.
Give it a way to check its work. Tell it what matters and when to ask for help.
3
30
1,124
This is a good day for open-source software!
CodeRabbit has pledged $1M in AI Security Deep Scans to OSS and now we have most powerful models to help bullet-proof the foundational software of that powers the internet for the next wave of cyber attacks.
CodeRabbit is joining the OpenAI Daybreak Defense Network.
CodeRabbit Secure now runs on GPT-6.1 Sol and OpenAI's GPT Cyber models. Early users have already found and fixed broken access controls and authentication failures with it.
Deep Scan is free until Nov 8, run it on your repo and see what it turns up.
@OpenAIDevs
coderabbit.ai/blog/one-milli…
3
218
For SF @Techweek_, I gave a talk at @Intuit about where we’re taking CodeRabbit: scaling engineering judgment as agents write more code.
Helping developers understand changes, check that they match their intent, and decide what should ship.
Full talk below.
Anyone else joining for @OpenAI’s DevDay in Berlin tomorrow?
Would love to connect!
