iCreatAI News
Skip to content
Trending storyWatching

Linear changes code review: AI reviews first, authors can merge their own changes

1 reports1 sources1 days agoUpdated

Understand this story

AI overview

The Linear engineering team has adjusted its code review process: each PR is first reviewed by an agent, and after the author addresses the feedback, they can approve and merge it themselves if they are confident in the changes; a second-person review is no longer a default requirement but remains optional. Changes involving sensitive areas such as authentication, infrastructure, and deployment configuration must be reviewed by a second human reviewer, and this requirement is automatically enforced before merging. According to data published by Linear, from January to October 2026, its number of merged PRs rose from 2,111 to 5,341, merged PRs per human author per month rose from 36 to 72, and the share of merged PRs reviewed by the author alone rose from 1% to 53%.

AI overview based on source reports · Updated 1 days ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. Hacker News AI
    Linear changed code review for AI-written code

    Linear describes how, as AI agents took on more implementation work, it moved from requiring two human reviewers on every change to agent-first review with author self-approval, keeping a second human review mandatory only for sensitive areas like authentication, infrastructure, and deployment configuration. Between January and October 2026, merged PRs rose 153% (2,111 to 5,341) while human authors grew 22% (58 to 71), and the share of PRs merged without a second human review climbed from 14% in July to 53% in October. The post also covers practices like fast feedback and reversibility, using working code to inform decisions, and asking agents to attach evidence such as screenshots or benchmarks to draft PRs.

Activity for this story

Current comparable activity
4
Peak comparable activity
10Nov 17 05:00
Change in the past 24 hours
-50%

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.