Re: PSA: Automatic Minutes Generation

Eric Rescorla <ekr@rtfm.com> Tue, 04 November 2025 15:37 UTC

Return-Path: <ekr@rtfm.com>
X-Original-To: wgchairs@mail2.ietf.org
Delivered-To: wgchairs@mail2.ietf.org
Received: from localhost (localhost [127.0.0.1]) by mail2.ietf.org (Postfix) with ESMTP id 9998F8299671 for <wgchairs@mail2.ietf.org>; Tue, 4 Nov 2025 07:37:38 -0800 (PST)
X-Virus-Scanned: amavisd-new at ietf.org
X-Spam-Flag: NO
X-Spam-Score: -1.897
X-Spam-Level:
X-Spam-Status: No, score=-1.897 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_NONE=0.001] autolearn=ham autolearn_force=no
Authentication-Results: mail2.ietf.org (amavisd-new); dkim=pass (2048-bit key) header.d=rtfm-com.20230601.gappssmtp.com
Received: from mail2.ietf.org ([166.84.6.31]) by localhost (mail2.ietf.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 3fUZKZVujt3X for <wgchairs@mail2.ietf.org>; Tue, 4 Nov 2025 07:37:37 -0800 (PST)
Received: from mail-yx1-xb12c.google.com (mail-yx1-xb12c.google.com [IPv6:2607:f8b0:4864:20::b12c]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature ECDSA (P-256) server-digest SHA256) (No client certificate requested) by mail2.ietf.org (Postfix) with ESMTPS id A1CB6829956E for <wgchairs@ietf.org>; Tue, 4 Nov 2025 07:37:01 -0800 (PST)
Received: by mail-yx1-xb12c.google.com with SMTP id 956f58d0204a3-63d97bcb898so8234405d50.0 for <wgchairs@ietf.org>; Tue, 04 Nov 2025 07:37:01 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rtfm-com.20230601.gappssmtp.com; s=20230601; t=1762270621; x=1762875421; darn=ietf.org; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=MxJdvNU2hIF7w0XoKNhBLib15s5AjBHJNV1+eP2Wvsc=; b=nRxRKZtmFu2MWY5Il8LOep3v0BDruW/G9SamkBPGYUBFsC97lS9RFDdSgTblMUMabB JCwoSJv00DRuoB6oDm6wo8dRsePssLiDp4lduBFes9XD4npWe4cFBCrD1z0JXmu18kkS qJW48z7Eecdr8FKHnJ0GvFyXybnIKX6UDR4xJFsYGaYIp77urJkDzcY897INZuR9j9sq EPbOotOKVPmukQKx9qM5qNzH4khL/EEq7v5FYsBmr59PVu0Oml6MNobAhNAoDmqlx59C Hh0Jw/be/SgjcY4nucppT9OiKylcv2jTJpBVrVFQ553ZNuK2Y+mufA3xco+6e1NglymM eckg==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1762270621; x=1762875421; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=MxJdvNU2hIF7w0XoKNhBLib15s5AjBHJNV1+eP2Wvsc=; b=gBnTVAowcEbwNORgRFsszuNoVpzsljrMlCX3q1gwSHvJA8mXXmornYAx0CnMiE4nOy sTN7terSXpfpfsMi7xVvlx4sfwFs31NYpgXuSsbLeXqsZIuv531GbOXQW/1229RQk8p+ cB1hJbSZ9JJVZjsdODPGeZPZaaV6FKP42wdkzYqdrnBADUECk7RaAYdI087yWpPQ4zD+ 3U9cLp0KuSLcp11oaN5CnfSXPzyjfzZ5lEr74lh6dYdR733I8NbWJk/O7um/RtNPgwXY pa1dkzOpNdMB/sD81QmPYzSTJMIuL65ndH1xIGlrnTtk9aXi5IRKDEnS8ApJYsEBx5mU Gvzw==
X-Forwarded-Encrypted: i=1; AJvYcCU9uaC9vBd1MFkaRB+NTYMAAgeJhT1aHON3tWXLxY9tmK+6je8fwkyVdaw5Gdjj8RRoUihuc3axog==@ietf.org
X-Gm-Message-State: AOJu0YzsE0/aS88qWASE/f2nkOUEV9rcKTih7IgksRjv54yLxT3HGB/l GIvE7Sj+4QccTQ6kF60UQWD2s8hzGFVQGRbV6TuKY36S4+J51+nmGwWoBNJbQ4MkbuUIqTblbkc mFpWgSIM0WlzQMrJQl0/nCVn/GcZBBg0cHBIiSL0y0w==
X-Gm-Gg: ASbGnct7zGIbxjZFmdsFmUTTE4CCFR3I5WY6AchyWYlc5DASfsY2E9y/6d4Ojaerznj usO1L5b95vbcEhlfSWVSSfJvEDyuRk6nHK3heGcNK6tFezjthC0ijVPeXv/I9tWuQHgRXpyzry8 ZJI+iCqJs+s5tCVahx3LaTj48p5qTbagPDwuksTsavlKhLnwAAesWF5ql0LsmqtmYl3LtXnhvZk LbbfLcqqQ1BEqQuxHUnAQFXO1sT+fOb3KZnx4SCVBa+Dul9kpDBn0oDyuGHlRvPisqxH3XIgfw7 rNqPBNv6nVxJP/RyvKzAmU1Ciyawbn/XGQRX9sBY5byYufKsLB8ZoxnOdugpYo/PUvP/WmY2Y8+ ffDg85/4q4YudN9bTpv/3bRyt6srf
X-Google-Smtp-Source: AGHT+IG/Yf7bscQA4OZQQ9Dtb05WamrPD+LF6R4FLAXDJG0HpDt6ChOBqZ25H5zjzEkjaWGj+UfXe3pYwHig2qxSKPg=
X-Received: by 2002:a05:690e:4294:20b0:63f:c019:23bc with SMTP id 956f58d0204a3-63fc766d87fmr2582144d50.27.1762270620992; Tue, 04 Nov 2025 07:37:00 -0800 (PST)
MIME-Version: 1.0
References: <CABcZeBOG5=c-c=RwLAGBotYAb+CJX5xomaM67R3aoascJ4Vc-A@mail.gmail.com> <CABcZeBP+B5SiW_5QX0KjSqLtoeq_AjT3ZY5dOkJ8tGFHiqgRpg@mail.gmail.com> <CADNypP8_UV86to1B3jmvqs6R90LOHCee4TU7M7BTsLYPVyVLwA@mail.gmail.com> <518D5861-AD38-43D1-BA23-A36574132CDB@gmail.com> <AS1PR07MB85892ABCB2A6C0522B511083E0C4A@AS1PR07MB8589.eurprd07.prod.outlook.com>
In-Reply-To: <AS1PR07MB85892ABCB2A6C0522B511083E0C4A@AS1PR07MB8589.eurprd07.prod.outlook.com>
From: Eric Rescorla <ekr@rtfm.com>
Date: Tue, 04 Nov 2025 07:36:25 -0800
X-Gm-Features: AWmQ_bna-ip3eQjQGVjWOTBciKqlJtb2WycGCAOQrovwnTXWk0s3-8lInpyqvo0
Message-ID: <CABcZeBP0xo3iMmh5ih=rOnbtDkKH=XBGNjo_SAn_MZoG=0D0fQ@mail.gmail.com>
Subject: Re: PSA: Automatic Minutes Generation
To: "Gunter van de Velde (Nokia)" <gunter.van_de_velde@nokia.com>
Content-Type: multipart/alternative; boundary="0000000000005cd8970642c69aad"
Message-ID-Hash: 2GUVYRIZA5XJ267XJT7LBHS3WHSA4MMC
X-Message-ID-Hash: 2GUVYRIZA5XJ267XJT7LBHS3WHSA4MMC
X-MailFrom: ekr@rtfm.com
X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; header-match-wgchairs.ietf.org-0; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header
CC: Working Group Chairs <wgchairs@ietf.org>
X-Mailman-Version: 3.3.9rc6
Precedence: list
List-Id: Working Group Chairs <wgchairs.ietf.org>
Archived-At: <https://mailarchive.ietf.org/arch/msg/wgchairs/-_rO_Rtrhgjzbadq9O_DOhqu3s0>
List-Archive: <https://mailarchive.ietf.org/arch/browse/wgchairs>
List-Help: <mailto:wgchairs-request@ietf.org?subject=help>
List-Owner: <mailto:wgchairs-owner@ietf.org>
List-Post: <mailto:wgchairs@ietf.org>
List-Subscribe: <mailto:wgchairs-join@ietf.org>
List-Unsubscribe: <mailto:wgchairs-leave@ietf.org>

On Tue, Nov 4, 2025 at 7:11 AM Gunter van de Velde (Nokia) <
gunter.van_de_velde@nokia.com> wrote:

> I suspect the Q was if the AI generated output can be kept at the same
> location but slightly updated by the chairs to avoid a too big discrepancy
> between these minutes and the IETF uploaded minutes.
>

This is certainly technically possible. The AI-generated summary is all in
GitHub (https://github.com/ietf-minutes/ietf-minutes-data/tree/cache) so
in principle the chairs could just do a PR against it. [0]  However, this
seems to have an obvious authorization problem in that I don't know which
PRs to approve. I think perhaps a better approach would be to automatically
detect when the official minutes were sourced from the auto-generated
minutes and then backport the changes to the site.

With all that said, this is all kind of working around the fact that this
is a separate service from the IETF minutes. If enough people are using
ietfminutes.org as the source for their minutes for this to be a real
problem, the right answer is probably to try to merge this functionality
into datatracker.



> Btw, this tool looks great. Thanks
>

You're welcome. I'm glad people are finding it useful.

-Ekr

[0] Right now, this cache is kind of soft state to avoid hitting the LLM
too hard, though it also makes sure the minutes are stable, so I'd need
to make sure that once a human touched it it didn't change.

G/
> (wearing no hats)
>
> -----Original Message-----
> From: Suresh Krishnan <suresh.krishnan@gmail.com>
> Sent: Tuesday, November 4, 2025 9:34 AM
> To: Rifaat Shekh-Yusef <rifaat.s.ietf@gmail.com>
> Cc: Eric Rescorla <ekr@rtfm.com>; Working Group Chairs <wgchairs@ietf.org>
> Subject: Re: PSA: Automatic Minutes Generation
>
>
> CAUTION: This is an external email. Please be very careful when clicking
> links or opening attachments. See the URL nok.it/ext for additional
> information.
>
>
>
> Hi Rifaat,
>   I think the intent is that the chairs will take this text as the input,
> make the necessary updates/changes and upload them into the official
> minutes.
>
> Regards
> Suresh
>
> > On Nov 4, 2025, at 9:17 AM, Rifaat Shekh-Yusef <rifaat.s.ietf@gmail.com>
> wrote:
> >
> > Hi Ekr,
> >
> > This looks great!
> > Is there a way for the WG chairs to make updates/changes to these
> minutes?
> >
> > Regards,
> >  Rifaat
> >
> >
> > On Mon, Nov 3, 2025 at 3:32 PM Eric Rescorla <ekr@rtfm.com> wrote:
> > Update:
> > I am generating live-ish minutes for IETF 124 at:
> > https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fietf
> > minutes.org%2Fminutes%2Fietf124%2Findex.html&data=05%7C02%7Cgunter.van
> > _de_velde%40nokia.com%7C85dba36496204f0e49c908de1baf51cd%7C5d471751967
> > 5428d917b70f44f9630b0%7C0%7C0%7C638978636956150734%7CUnknown%7CTWFpbGZ
> > sb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOI
> > joiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=GFe1EpM8bN7SNZ3knertD7M
> > G26DxXMMTnPtIM21MEi8%3D&reserved=0
> >
> > It takes some time for Meetecho to produce the transcripts, so they're
> > not available right after the meeting, but as a reference point Monday
> > Session I is now available.
> >
> > -Ekr
> >
> >
> > On Sat, Oct 11, 2025 at 7:02 PM Eric Rescorla <ekr@rtfm.com> wrote:
> > Hi Chairs,
> >
> > Like many of you, I've long been unsatisfied with the situation around
> > IETF minute taking, in which we conscript someone into taking minutes,
> > thus preventing them from fully participating, and often with mediocre
> > results.
> >
> > In an attempt to partly address this situation, I've put together an
> > automatic minutes generator at
> > (https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fiet
> > fminutes.org%2F&data=05%7C02%7Cgunter.van_de_velde%40nokia.com%7C85dba
> > 36496204f0e49c908de1baf51cd%7C5d4717519675428d917b70f44f9630b0%7C0%7C0
> > %7C638978636956180260%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUs
> > IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7
> > C0%7C%7C%7C&sdata=rLBw8VUpjTt2WEJgbHkmsjgrgn%2B9%2BQ4GS4WwVX%2FW%2Fio%
> > 3D&reserved=0). The site takes as input the Meetecho transcript and
> > produces AI-generated minutes. I've gone back and made minutes through
> > IETF 112 (November
> > 2021) and I plan to produce minutes for IETF 124 (Montreal) once
> > transcripts are available, shortly after the meeting.
> >
> > Hopefully others will find this useful.
> >
> > -Ekr
> >
> > P.S. I'm not a WG chair, so you should make sure to keep me on CC if
> > you want a response.
>
>