Wednesday, November 18, 2026
  • Login
  • Register
Technology Tutorials & Latest News | ByteBlock
  • Home
  • Tech News
  • Tech Tutorials
    • Networking
    • Computers
    • Mobile Devices & Tablets
    • Apps & Software
    • Cloud & Servers
    • IT Careers
    • AI
  • Reviews
  • Shop
    • Electronics & Gadgets
    • Apps & Software
    • Online Courses
    • Lifetime Subscription
No Result
View All Result
Tech Insight: Tutorials, Reviews & Latest News
No Result
View All Result
Home News Google

Lessons from building Sashiko, an agentic code review system

November 18, 2026
in Google
0 0
0

This all tracks with what Linus Torvalds wrote in a mailing-list discussion a few weeks after Sashiko’s launch:

“As you say, Sashiko tends to be quite good. Even when it flags something unnecessarily and there’s no actual problem, there’s likely to be a reason for the question. And we’ve seen some truly stellar reports too. Things that are deep and subtle, and the AI is 100% correct. So anybody who thinks that all AI is slop is in denial about the current state.” – Linus Torvalds (on lore.kernel.org)

Sashiko at a glance

Since March 2026

Patch reviews completed

241,000 (~1200+ / day)

Opted-in kernel subsystem lists

75+

Mainline commits crediting Sashiko

2,000+

2026 Linux kernel CVEs crediting Sashiko

528

60-day post-merge fix rate

Down from 3.4% baseline to 2.2% (Linux 7.2)

What we learned from building and running Sashiko

First, benchmark-driven development beats intuition. While developing Sashiko, we tried many ideas that looked very reasonable on their face but didn’t end up working out. Other ideas were less obvious but worked surprisingly well. What was crucial: Early on, we built a benchmark out of nearly 1,000 real Linux kernel bugs and used it to evaluate every major Sashiko change. Every bug in this set was a real mistake that had passed human review by kernel experts, had been merged into mainline Linux, and later had to be fixed. On that benchmark, Sashiko with the new Gemini 4 Carbon model catches 75.8% of the bugs that human reviewers missed (using high thinking level).

Second, coding agents are not great at reviewing their own code. Models are trained to produce a working solution within a limited token budget. Asking these agents to review their own code might work well for isolated tasks, but for real, large codebases, creating a functional solution is often just 5-10% of the work. What’s really hard is to produce a solution that works all of the time, is well-integrated into the surrounding code, and doesn’t introduce subtle regressions. This is often substantially more complex and requires additional effort. Similar to human developers, agents benefit from external code review: Reviewers often spot issues that the initial author missed, even if they are not more experienced.

Third, open source and shared community ownership and development help to build trust. By being fully open and transparent from the beginning, Sashiko allowed anyone to run it the way they wanted: using different models (including open source and local models), customizing prompts, or even adopting Sashiko to other-than-Linux projects. This helped with community adoption and brought over 100 contributors to improve Sashiko, including some prominent kernel developers.

More and more engineers are putting local Sashiko instances into their coding-agent loops, so patches are checked against the community’s review rules before a human maintainer ever sees them. We use the same workflow to build Sashiko itself (“Sashiko for Sashiko”), running it to review every change to its codebase and prompt pipeline both locally and through a Github integration.

Although Sashiko started in the Linux kernel, the need for an agentic trust layer applies across critical open-source software. Because the core review engine does not depend on C or on kernel-specific rules, the Linux kernel playbook (combining an open verification pipeline, community-owned domain guides, and a benchmark mined from historically known issues and fixes) can likely be applied to other foundational open-source projects such as GCC, LLVM, or Git.

“Now, I think the other side of AI – and this is where Sashiko comes in – is that it basically does end up being a tool that can then increase the trust in the patch. So AI giveth, and AI taketh away. But the basic issue shouldn’t be AI per se, it should be that notion of ‘trust’.” – Linus Torvalds on LKML

You can check out Sashiko at sashiko.dev, or find the code on GitHub to run it in your own development workflow.

ShareTweetShare
Previous Post

The Envoy agentic stack: Routing models, tokens, and MCP

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

You might also like

Lessons from building Sashiko, an agentic code review system

November 18, 2026

The Envoy agentic stack: Routing models, tokens, and MCP

November 18, 2026

Google Cloud Highlights EMEA Startup Momentum at Slush 2026

November 18, 2026

A bridge to modernization: What IDC’s Market Note says about Cameyo by Google

November 18, 2026

Modern data visualizations and custom charts in Looker

November 18, 2026

2026 Google Cloud Partner All-stars Winners

November 18, 2026
monotone logo block byte

Stay ahead in the tech world with Tech Insight. Explore in-depth tutorials, unbiased reviews, and the latest news on gadgets, software, and innovations. Join our community of tech enthusiasts today!

Stay Connected

  • Home
  • Tech News
  • Tech Tutorials
  • Reviews
  • Shop
  • About Us
  • Privacy Policy
  • Terms & Conditions

© 2024 Byte Block - Tech Insight: Tutorials, Reviews & Latest News. Made By Huwa.

Welcome Back!

Sign In with Google
Sign In with Linked In
OR

Login to your account below

Forgotten Password? Sign Up

Create New Account!

Sign Up with Google
Sign Up with Linked In
OR

Fill the forms below to register

*By registering into our website, you agree to the Terms & Conditions and Privacy Policy.
All fields are required. Log In

Retrieve your password

Please enter your username or email address to reset your password.

Log In
  • Login
  • Sign Up
  • Cart
No Result
View All Result
  • Home
  • Tech News
  • Tech Tutorials
    • Networking
    • Computers
    • Mobile Devices & Tablets
    • Apps & Software
    • Cloud & Servers
    • IT Careers
    • AI
  • Reviews
  • Shop
    • Electronics & Gadgets
    • Apps & Software
    • Online Courses
    • Lifetime Subscription

© 2024 Byte Block - Tech Insight: Tutorials, Reviews & Latest News. Made By Huwa.

Login