12:04:37 <RRSAgent> RRSAgent has joined #adapt
12:04:41 <RRSAgent> logging to https://www.w3.org/2025/09/23-adapt-irc
12:04:41 <Zakim> RRSAgent, make logs Public
12:04:42 <Zakim> please title this meeting ("meeting: ..."), janina
12:04:54 <janina> Meeting: WAI-Adapt Teleconference
12:05:08 <janina> Date: 23 Sep 2025
12:05:13 <janina> Chair: Janina
12:05:43 <janina> regrets: Russell, Annalu, Lionel
13:58:04 <janina> present+
13:59:39 <hadleybeeman> hadleybeeman has joined #adapt
14:00:29 <janina> zakim, who's here?
14:00:29 <Zakim> Present: janina
14:00:31 <Zakim> On IRC I see hadleybeeman, RRSAgent, Zakim, janina, gb, Roy_Ruoxi, jcraig
14:02:52 <hadleybeeman> hadleybeeman has joined #adapt
14:02:56 <Abhinav> Abhinav has joined #adapt
14:03:07 <Abhinav> present+
14:03:54 <matatk> matatk has joined #adapt
14:04:38 <hadleybeeman> hadleybeeman has joined #adapt
14:05:48 <janina> scribe+
14:05:51 <hadleybeeman> hadleybeeman has joined #adapt
14:08:34 <janina> topic: Renaming WKD
14:09:43 <janina> janina: Thinking 'common' or 'discoverable'
14:10:15 <matatk> Naming discussion from the 9th: https://www.w3.org/2025/09/09-adapt-minutes.html#59b0
14:12:09 <janina> matatk: Really like discoverable
14:12:26 <janina> matatk: Goes with the html ethos of discoverable metadata
14:13:21 <janina> janina: possibly also 'standard'
14:13:47 <janina> matatk: maybe discvoerable common destinations'
14:15:33 <janina> rrsagent, make minutes
14:15:34 <RRSAgent> I have made the request to generate https://www.w3.org/2025/09/23-adapt-minutes.html janina
14:15:44 <janina> matatk: Recall us suggesting 'way points'
14:15:59 <janina> matatk: Also 'familiar' or ' core' from Lionel previously
14:16:13 <janina> rrsagent, make minutes
14:16:14 <RRSAgent> I have made the request to generate https://www.w3.org/2025/09/23-adapt-minutes.html janina
14:16:20 <matatk> s/way points/waypoints/
14:16:51 <janina> janina: 'WAIpoints' ??
14:18:00 <janina> matatk: 'sign posts'
14:19:03 <matatk> s/sign posts/signposts/
14:19:05 <janina> topic: Agentic PR
14:19:42 <matatk> scribe+
14:19:45 <matatk> Abhinav: https://github.com/w3c/adapt/pull/326
14:19:57 <matatk> janina: I really like it, I think it's really well written. My only two concerns...
14:20:36 <matatk> ... (1) we're not tying any of our remit in here - everything you say I think is true, but our remit is that it's tied to accessibility, but that's not clear. Maybe we can cross-reference some requirements in here.
14:20:59 <matatk> Abhinav: I think it's related to accessibility in that, at the end of the day, these tools help you to do jobs.
14:21:07 <matatk> janina: I agree, but we need to make that clearer. Then the other thing...
14:21:28 <matatk> ... (2) MCP figures in there very prominently. I think maybe that's good. But is that an open protocol, or is it in IETF?
14:21:34 <matatk> Abhinav: It's a protocol from Anthropic
14:21:35 <matatk> q+
14:21:43 <matatk> Abhinav: It's open source
14:21:47 <matatk> janina: That's a company.
14:22:03 <matatk> janina: that may or may not be a problem; I don't know.
14:22:17 <matatk> ... beyond that I had some minor points of writing style.
14:22:22 <matatk> ... need to credit Abhinav
14:22:29 <matatk> ack me
14:22:53 <janina> matatk: With respect to MCP, there are some concerns; were discussed at TAG
14:23:28 <janina> matatk: There are others, but this one seems to be the favorite suddenly
14:23:51 <janina> matatk: W3C is considering where to focus
14:26:44 <janina> q+
14:27:26 <janina> matatk: mcp is being considered in a WG; but it's so recent
14:28:11 <janina> ack ja
14:28:33 <matatk> janina: Can we re-phrase and use MCP as an example. What is the (taxonomic) service that MCP is providing?
14:28:51 <matatk> Abhinav: from perspective of agentic systems, there's a 'brain' which is an LLM and a tool that's performing what it's told.
14:28:58 <matatk> ... simple e.g.  planning a vacation
14:29:07 <matatk> ... MCP is a protocol to expose those tools and resources needed.
14:29:41 <matatk> ... MCP is being used to expose the tools, but we can always talk about tools in general, and their relation to LLMs. That arrangement will persist, but protocols may change.
14:29:46 <matatk> janina: is it a request broker?
14:29:56 <matatk> Abhinav: can be seen a bit like that.
14:30:16 <matatk> janina: so we could say 'a good request broker, example MCP' so we are not closing on it, but it's an example of the function.
14:30:35 <matatk> Abhinav: OK, will try to figure out the best common word, and use MCP as exaple.
14:30:38 <matatk> q+
14:30:46 <janina> ack ma
14:30:59 <janina> matatk: have some specific comments -- now or off line?
14:32:10 <janina> matatk: Reiterating some comments, esp we shouldn't standardize just for machines
14:33:08 <janina> matatk: but if we tie to a11y, perhaps most of the contents moves to the main explainer, or phps to the RQTF AI-A11y pepr as an example of agentic functionality
14:33:36 <Abhinav> q+
14:34:07 <matatk> ack Abhinav
14:34:08 <janina> ack a
14:34:18 <janina> Abhinav: agree to the existing explainer
14:34:45 <janina> Abhinav: wonders process; should we post and then see where we want to move things?
14:36:22 <janina> matatk: suggests anything that might be removed at least to an appendix so we don't lose any of this wonderful work
14:39:00 <janina> janina: general agreement to move to a WD and then copy, move, etc, as seems best
14:40:17 <janina> topic: Possible Synergies
14:40:41 <janina> matatk: Describing TAG discussion related ...
14:41:16 <matatk> https://github.com/w3ctag/meetings/blob/gh-pages/2025/09-Hong-Kong/09-16-minutes.md#mcp
14:51:25 <matatk> janina: Two kinds of simplification: content, and interaction UI.
14:57:30 <matatk> matatk has left #adapt
14:58:57 <janina> zakim, end meeting
14:58:57 <Zakim> As of this point the attendees have been janina, Abhinav
14:58:58 <Zakim> RRSAgent, please draft minutes
14:58:59 <RRSAgent> I have made the request to generate https://www.w3.org/2025/09/23-adapt-minutes.html Zakim
14:59:05 <Zakim> I am happy to have been of service, janina; please remember to excuse RRSAgent.  Goodbye
14:59:07 <Zakim> Zakim has left #adapt
15:01:47 <hadleybeeman> hadleybeeman has joined #adapt