Review Linux kernel patches
Google engineers launched Sashiko, an agentic AI code reviewer for the Linux kernel.
Done with a custom-built or unnamed agent
- What they did
- Roman Gushchin's team at Google spent several months building Sashiko, an agentic code review system, and used it internally before release. It is now open source and covers every submission to the Linux kernel mailing list. It was designed for Gemini 3.1 Pro but should also work with Claude and probably other LLMs.
- How it went
- On 1,000 recent upstream issues with Fixes: tags, it found about 53% of the bugs, and human reviewers had missed all of them. Gushchin acknowledges that 53% may not sound impressive.
- Worth knowing
- Google is paying for the token budget and infrastructure while hosting moves to the Linux Foundation, so running this yourself means covering your own LLM costs.
Try it yourself with Codex
Act as a code reviewer for this patch or diff: [paste diff or give branch name] in the repo at [path]. Check for bugs, memory or concurrency problems, missing error handling, and unclear naming, citing exact lines. Finish with a prioritized list of findings and a one-paragraph verdict on whether it's ready to merge.
Discussion on HN · Mar 18, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
- Custom agent
Catch cloud outage risks before they happen
An autonomous ReAct agent that queries real data to stop cloud outages before they occur, built for the Sanity Challenge.
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Migrate toolchain, architecture and site design with Claude Code
A developer had Claude Code switch a monorepo to oxlint/oxfmt, restructure the architecture and redesign a site, validating in a loop; the redesign took days instead of weeks.
Build and deploy a Game of Life simulation site
In a vendor launch demo, Devin built an interactive Game of Life website, added requested features step by step, and deployed it to Netlify.
Resolve a Slack-reported issue with a coding agent
A Codex agent resolved an issue passed to it in about 40 minutes, and an ops agent verified the fix back in Slack.