All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: "Michael S . Tsirkin" <mst@redhat.com>,
	"Alex Bennée" <alex.bennee@linaro.org>,
	"Alistair Francis" <alistair.francis@wdc.com>,
	"BALATON Zoltan" <balaton@eik.bme.hu>,
	"Daniel P . Berrangé" <berrange@redhat.com>,
	"Fabiano Rosas" <farosas@suse.de>,
	"Kevin Wolf" <kwolf@redhat.com>,
	"Peter Maydell" <peter.maydell@linaro.org>,
	"Warner Losh" <imp@bsdimp.com>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>
Subject: [PATCH 3/4] AGENTS.md: make the human part of the design process
Date: Tue,  1 Sep 2026 18:14:21 +0200	[thread overview]
Message-ID: <20260901161422.314581-4-pbonzini@redhat.com> (raw)
In-Reply-To: <20260901161422.314581-1-pbonzini@redhat.com>

This came out of the experiment with the first version of the AGENTS.md
file, corresponding to the previous commit.  This addition improved the
behavior of the agent from the very beginning.  The very first answer to
the same prompt in fact was "I'll orient in the codebase first, then we
should talk about design choices before I write anything".

In fact, after thinking it pointed out from the start that this requires
pre-arrangement and asked two questions (how to represent the pressure and
temperature in the QOM properties, how much of the behavior to implement).
Even with a single data point it seems worth trying.

When asked to commit autonomously, the LLM also clarified that it
wouldn't add S-o-b trailers and that pre-arrangement was on me.
It included "Message written by an AI and to be rewritten by hand; not
for submission as is" in the commit message, a "handover notes"
section about design choices that were made without the user input,
and the umpteenth reminder that the work may only be posted if a
maintainer has agreed beforehand to review them.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 AGENTS.md | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/AGENTS.md b/AGENTS.md
index 8fb96ebfc38..c3cb6978191 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -66,6 +66,22 @@ In order to protect the project's scarcest resource, which is review time:
 - You must **tell humans about these expectations** at handover.  Even
   when they are engaging actively, remind them about the parts of the
   work they have not examined.
+- When handing over text that the maintainers may see, remind the human
+  that it is a draft and name any design choices that are still open
+
+### Make the human part of the design process
+
+In order to guide the design rather than providing an all-encompassing
+solution:
+
+- You must **discuss design choices in the main conversation**.  Delegate
+  research to sub-agents but not judgment, and do not treat your own
+  reasoning as a substitute for the conversation.
+- When you consult a subagent, **report what it recommended** and
+  possibly confirm the choice, rather than simply presenting the outcome.
+- Reinstate as visible text any design decision made while thinking.
+  Design decisions hidden within thinking blocks prevent the human
+  from building familiarity with the contribution.
 
 ### AI usage must be disclosed and/or pre-arranged
 
-- 
2.55.0



  parent reply	other threads:[~2026-09-01 16:15 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-01 16:14 [RFC PATCH v2 0/4] docs/devel, AGENTS.md: a completely new policy on AI-generated contributions Paolo Bonzini
2026-09-01 16:14 ` [PATCH 1/4] docs/devel: introduce a " Paolo Bonzini
2026-09-02  1:38   ` Alistair Francis
2026-09-02  7:09     ` Paolo Bonzini
2026-09-02  9:41       ` Michael S. Tsirkin
2026-09-02 10:08       ` Daniel P. Berrangé
2026-09-02 12:01   ` Peter Maydell
2026-09-03  1:39     ` Alistair Francis
2026-09-03  7:09     ` Paolo Bonzini
2026-09-02 16:09   ` Daniel P. Berrangé
2026-09-03 10:05     ` Paolo Bonzini
2026-09-01 16:14 ` [PATCH 2/4] AGENTS.md: Let agents know what the participation rules are Paolo Bonzini
2026-09-02  1:44   ` Alistair Francis
2026-09-02 16:26     ` Daniel P. Berrangé
2026-09-02 17:45       ` Paolo Bonzini
2026-09-02 13:42   ` Alex Bennée
2026-09-02 13:47     ` Daniel P. Berrangé
2026-09-02 13:56       ` Michael S. Tsirkin
2026-09-02 14:08         ` Daniel P. Berrangé
2026-09-02 15:15           ` Michael S. Tsirkin
2026-09-02 13:48     ` Michael S. Tsirkin
2026-09-01 16:14 ` Paolo Bonzini [this message]
2026-09-02  1:44   ` [PATCH 3/4] AGENTS.md: make the human part of the design process Alistair Francis
2026-09-01 16:14 ` [PATCH 4/4] agents: add CLAUDE.md and GEMINI.md Paolo Bonzini
2026-09-02  1:47   ` Alistair Francis
2026-09-02  4:45     ` Philippe Mathieu-Daudé
2026-09-02  9:46   ` Michael S. Tsirkin
2026-09-02  9:56     ` Paolo Bonzini
2026-09-02 10:06       ` Michael S. Tsirkin
2026-09-02 10:12         ` Daniel P. Berrangé
2026-09-02 13:04           ` Michael S. Tsirkin
2026-09-02 14:30             ` Paolo Bonzini
2026-09-02 15:54 ` [RFC PATCH v2 0/4] docs/devel, AGENTS.md: a completely new policy on AI-generated contributions Peter Maydell
2026-09-02 17:50   ` Alex Bennée
2026-09-03 11:29   ` BALATON Zoltan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260901161422.314581-4-pbonzini@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=alex.bennee@linaro.org \
    --cc=alistair.francis@wdc.com \
    --cc=balaton@eik.bme.hu \
    --cc=berrange@redhat.com \
    --cc=farosas@suse.de \
    --cc=imp@bsdimp.com \
    --cc=kwolf@redhat.com \
    --cc=mst@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.