IndustryMulti-source

CodeRabbit 月烧 25 万美元 AI 费用、一个月合出 5000 个 PR 的运作方式

Why we picked it

一家公司每月花 25 万美元让 agent 写代码,一个月合了 5000 个 PR。最狠的是被报价 1300 万的 CI,自己用 agent 一周做出来还便宜一半。代码审查被替换成了 release 审查,写代码的人应该听听他们怎么运转的。

CodeRabbit 创始人 Harjot Gill 在 Gergely Orosz 的播客中透露,公司上月花费 25 万美元运行 AI agents,一个月内合入了超过 5000 个 pull requests。

Body

内部机制上有几个关键做法:工程师不再逐个 PR 做代码审查,而是审查包含多个 PR 的 release;他们的 AI 支出更像是研发投入,因为产出会被转化为可售卖的新产品功能。被报价 1300 万美元/年的 CI 方案后,Gill 用 agents 自建了一套 CI 系统,耗时一周,成本比报价低 50%,性能相当。

招聘方面,Gill 发布了一份非常规职位广告:只邀请过去 30 天内提交过 1000 个以上非水货 PR 的候选人,或玩过 500 小时以上《文明》《Factorio》等策略经营游戏的工程师。他认为并行管理几十个 agent 与操作策略游戏中的多个单位是同一种能力,看重的是主动性、经验广度和系统思维。

Original · Gergely Orosz

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. https://t.co/w9y67Gs8ab

• @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. https://t.co/7yHVse7fpS

• @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. https://t.co/OzuIJ1wHtZ

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.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include CodeRabbit, AI agents, coding assistants, code review.

Source attribution: curated from Gergely Orosz (@GergelyOrosz). Cross-source corroboration: 3 independent sources have covered this development (including TestingCatalog, AutoGPT), confirming industry-wide signal strength.