CodeRabbit (@coderabbitai) header
CodeRabbit (@coderabbitai) profile picture

CodeRabbit helps teams review, understand, govern, and trust agent-generated code: https://www.teapawt.org/t.co/GxSOapi2As!

San Francisco, CA
Joined April 2023
Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)Photo by CodeRabbit (@coderabbitai)
Introducing CodeRabbit Verify Don't let your users be the first test run! > PR testing: catch broken features before merge > User journeys: confirm critical flows work before each release > Tickets and fixes: get reviewed, tested fixes for reported bugs In public beta now!
90
59
106
461
224,028
CodeRabbit retweeted
Introducing CodeRabbit Verify Don't let your users be the first test run! > PR testing: catch broken features before merge > User journeys: confirm critical flows work before each release > Tickets and fixes: get reviewed, tested fixes for reported bugs In public beta now!
90
59
106
461
224,028
CodeRabbit retweeted
How does a truly "AI-pilled" startup work? @harjotsgill spent $250K last month on AI agents, shipped 5,000 PRs and explains why this all makes sense - at least for CodeRabbit. Timestamps: 00:00 Intro 03:17 How Harjot shipped over 5,000 pull requests in a month 08:46 Harjot’s path into tech and his first startups 12:25 Early conviction around AI and founding CodeRabbit 14:40 Switching to AI coding 20:35 Software factories explained 25:37 What’s replacing human code review 38:44 Technical debt and deslopping tests 46:05 Evals 50:25 Formal methods 52:05 AI cost at CodeRabbit 54:57 Startup funding in 2026 and the value of AI spend 1:08:20 Hiring 1:13:03 Work pace, sleep, and burnout 1:21:55 Skills for the AI era 1:24:30 Book recommendation Brought to you by: • @turbopuffer – a ridiculously scalable, fast and cheap hybrid search engine, built on top of object storage, used by cutting-edge companies like Anthropic, Linear, Ramp and others. turbopuffer.com/pragmatic • @GoEntire – Entire launched its own Git forge, shipped Continuous Memory, and reinvented the pull request (called Trails). Trails are a much more natural workflow when agents keep pushing new changes. entire.io/pragmatic • @WorkOS – WorkOS built Airlock, the authorization layer for AI agents. It evaluates every request against the agent’s intent + your rules, and either allows it, denies it, or routes it to a human. workos.com/airlock Three interesting learnings: 1. For dev tooling startups like CodeRabbit, massive AI spend can be justified by launching new, AI-related products faster It feels to me that CodeRabbit is not a typical company: its AI spending is a form of R&D if it creates new solutions that can be commercialized and sold. It’s not the same at places with fixed customer bases willing to pay a certain amount for an existing product, and no more. Also, Harjot says that they got quoted $13M/year for a CI solution to handle their PR output, but the price made him decide they’d build their own CI system using agents. It took a week, and the new CI cost 50% less than the quote, with similar performance. 2. Human code review is dead, long live the human review! Harjot thinks that we will stop reviewing code generated by agents. Instead, we’ll spend more time reviewing the planning and final asset. Inside of CodeRabbit, engineers are reviewing releases (multiple PRs), not individual PRs. 3. What Harjot looks for when hiring engineers: agency, breadth of experience, and systems thinking. He posted an unconventional job ad, only inviting candidates who had shipped 1,000+, non-slop PRs in the past 30 days, or had played 500+ hours of strategy and management games like Civilization, Age of Empires, Transport Tycoon, or Factorio. Harjot says he cannot unsee the similarities between running dozens of agents in parallel and playing a strategy video game involving tracking what dozens of units do.
26
6
4
49
8,113
CodeRabbit retweeted
London it is! 🇬🇧 Excited for what we’ll build here!
12
7
4
59
6,482
CodeRabbit retweeted
new office, who dis
10
3
112
2,865
CodeRabbit retweeted
Agents now write code faster than any human can read it. The new bottleneck is how many sessions we can keep track of. Naturally the only fix was to spend an hour with @ryanvogel going deep on review, trust, and upstream problems.
9
8
1
27
2,915
Monday morning, last week’s PRs still haven’t shipped. Ugh. Now main has moved on and conflicts are piling up. Set up rules to triage everything automatically. Some customers already use them to merge PRs ~80% faster.
6
3
2
22
3,170
CodeRabbit retweeted
We are entering a golden era of systems engineering. What used to take tremendous skill can now be autonomously hill-climbed by agents within weeks, especially when there are only a few sound ways to get it right and the decision space is narrow. As the saying goes, if someone were to re-invent Unix, they would end up with Unix. Here are 5 examples of what we've recently built at CodeRabbit: 1. Git WAL: Git-compatible storage with immutable packs, manifest CAS, replay, checkpoints and geometric compaction. 265K+ knowledge repos. Peak: 82K HTTP requests/min. 431 PRs · 44K Rust LOC · 19 TLA+ / 1 Lean files · ~$44K estimated token spend.
12
6
2
93
22,019
Attackers have AI agents probing open-source code 24/7 & we think maintainers should too! CodeRabbit ran Deep Scans on 1,125 public repos with 1,215 high or critical findings, 75 of which are already fixed. Your first Deep Scan is on us, up to $1K for orgs with 2+ people.
121
385
102
978
940,690
CodeRabbit retweeted
CodeRabbit has hit $100 million in ARR, up 10x in just over a year. Teams send us 3 million+ pull requests a week, because the agent that wrote the code shouldn't be the one to approve it. We've grown so much that even Josh wants a job now!
21
29
28
148
28,287
CodeRabbit has hit $100 million in ARR, up 10x in just over a year. Teams send us 3 million+ pull requests a week, because the agent that wrote the code shouldn't be the one to approve it. We've grown so much that even Josh wants a job now!
21
29
28
148
28,287
Risk-based auto-approvals are live. 𝚛𝚎𝚟𝚒𝚎𝚠𝚜: 𝚊𝚞𝚝𝚘_𝚊𝚙𝚙𝚛𝚘𝚟𝚊𝚕𝚜: 𝚎𝚗𝚊𝚋𝚕𝚎𝚍: 𝚝𝚛𝚞𝚎 𝚖𝚊𝚡_𝚖𝚎𝚛𝚐𝚎_𝚛𝚒𝚜𝚔: 𝚕𝚘𝚠 𝚘𝚟𝚎𝚛𝚛𝚒𝚍𝚎𝚜: - 𝚙𝚊𝚝𝚑𝚜: ["𝚜𝚛𝚌/𝚊𝚞𝚝𝚑/**"] 𝚎𝚗𝚊𝚋𝚕𝚎𝚍: 𝚏𝚊𝚕𝚜𝚎 Cap the risk CodeRabbit can approve, and turn it off for sensitive paths or teams.
4
1
1
17
2,893