Re: AI-assisted review

[Michal Simek <michal.simek@amd.com>]

On 5/16/26 00:07, Tom Rini wrote:
> On Fri, May 15, 2026 at 03:03:21PM -0600, Simon Glass wrote:
> 
>> Hi,
>>
>> There was a query on the call this week about whether I am doing
>> AI-assisted code review. As I said on the call: yes. Here is a brief
>> description of how it works.
>>
>> It is built into Patman (on the Concept tree) with a new 'patman
>> review' command. You give it the series name / number, or perhaps a
>> patch name/number and it applies the patches to a new branch, does a
>> review then adds its comments to its database.
>>
>> A '-d' flag can be used to create draft emails in Gmail (sorry, it
>> doesn't support other email programs yet). You then check and update
>> the emails and send them (or delete them). I am not an expert in
>> handling the 'user voice' part of AI, but have made an attempt to make
>> it follow any provided configuration, as well as to scan recent
>> reviews to actually create to create a voice.
>>
>> Obviously this is very rudimentary and could be expanded considerably.
>> But the mere fact that it creates draft emails is a win for me, even
>> if I ultimately delete or rewrite most of the comments. I can imagine
>> 10 different ways to improve it to be more useful.
>>
>> I wrote a blog post about it if you want more details, or you can ask me here.
>>
>> I am very interested in hearing how others are using these new tools
>> for code review.
> 
> And the big thing for now is that since we as a project do not yet have
> an AI policy aside from "please don't". One of the points I was making
> on the call is that there's a difference in value between "Human
> reviewed it, looks fine" and "Human spent some tokens, agent didn't see
> any problems".
> 
> And I know several other people have been doing at least first pass
> reviews with various agent-tools, it's just no one else has been posting
> reviews at your scale. And lessons learned from other projects is that
> the prompts are more important than whatever wrapper around the agent
> one is using.
> 

Don't think scale is the problem. Tool and integration is another topic.
I think at the end of day it is about rules and creating u-boot specific
review prompts as it is done for Linux.
https://github.com/masoncl/review-prompts

I don't think that make sense to host it out of u-boot repo because even
we have some rules written in documentation. And it is up to everybody if they 
want to use this agent/model or at the end if this is something what should run
as the part of CI or so. It is just about rules and extending that rules to 
cover common mistakes.
Because truth is that after that years with project we see the same issues again 
and again. Formatting issues, broken kernel-doc, headers, etc.

The first pass can be simply read current documentation and covert it to new 
U-Boot rules and start with it. This should generated solid base for start.

Thanks,
Michal