AI Trends

Trending story

Harjot Gill Believes Humans Will Stop Reviewing Agent-Generated Code

1 reports1 story updatesUpdated Nov 19 02:08

Understand this story

Story summary

The English summary is being updated. See the reporting timeline below.

Latest development · Report

CodeRabbit CEO Harjot Gill on Software Factories and Code Review

Developments

1 confirmed developments

  1. English translation is being prepared.

    Source:Pragmatic Engineer

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 19

  1. Pragmatic EngineerSelected

    CodeRabbit CEO Harjot Gill on Software Factories and Code Review

    CodeRabbit CEO Harjot Gill described the company’s practice of building a software factory with large numbers of AI agents. He submitted more than 5,000 PRs last month, with his personal monthly AI spending at approximately $250K–$275K. CodeRabbit controls quality through formal methods, deterministic simulations, development-environment validation, and phased releases, and has shifted from reviewing individual PRs to reviewing plans and final deliverables. Harjot believes that human code review is losing its traditional role, while heavy AI investment is easier to justify for AI infrastructure startups that need to launch new products quickly.

Related stories

  1. Related storiesOpenAI releases GPT-6.2 Astra and Sol, ARC Prize announces perfect scores
  2. Related storiesAnthropic launches Claude Fable 5.2 and Claude Mythos 5.2
  3. Related storiesAnthropic Publicly Submits S-1 for Proposed Nasdaq IPO
  4. Related storiesOpenAI doubles the usage limits for Pro 100/200/500 and Business Premium