Re: Introduce Sashiko (agentic review of Linux kernel changes)

[Lorenzo Stoakes]

On Wed, Mar 18, 2026 at 02:50:42PM -0400, Chris Mason wrote:
> On 3/18/26 2:33 PM, Roman Gushchin wrote:
> > "Lorenzo Stoakes (Oracle)" <ljs@xxxxxxxxxx> writes:
> >>>
> >>> Finally, some subsystems have a good prompts coverage and some don't. It
> >>> doesn't have to be lengthy documentation (and it might actually be
> >>> counter-productive), but having a small list of things to look at - some
> >>> high-level concepts which are hard to grasp from the code, etc. - can
> >>> help a lot with both bug discovery and false positives.
> >>
> >> I guess best contributed to Chris's review-prompts repo right?
> >
> > Both works for me now, we'll figure out with Chris how to sync our
> > prompts. The small problem is that we're using various models, tools and
> > review protocols and barely can test each other's setup. And it's all
> > very fragile, so it's not exactly trivial.
> > But we'll figure out something soon.
> >
> > In general we need to carefully separate instructions (like which tools
> > to use, which prompts to load etc) from factual data. Then we can easily
> > use the factual data with various tooling around.
>
> I'm really excited to see Roman's work go live, and we've been talking
> about different ways to collaborate for a while.  I don't really have
> answers today other than just trying to iterate and do what works, but I
> wanted to reply that I'm fully supportive.

Ack, yes I'm very grateful for Roman's work, I think it's just a question of
figuring out how to fit things into our workflow effectively :)

Going to be a (possibly) bumpy ride but in general LLMs are _very good_ at this
kind of thing (code review, diagnostics), so it's an appropriate use of them and
in general I really feel we can catch a lot more bugs a lot sooner this way.

So, obviously modulo expressed concerns and details of how we do things, I'm
very much excited by and in favour of using AI for this kind of thing.

>
> -chris
>

Cheers, Lorenzo