[OPSAWG]Re: [nmrg] Re: [NMOP] Re: [OPSAREA@I ETF126] IRTF/IETF OPS Transfer: Status & Exploring Collabor ation Opportunities

<Thomas.Graf-Zc0CTiu5wcBWk0Htik3J/[email protected]> Thu, 9 Jul 2026 06:46:31 +0000
Newsgroups gmane.ietf.opsawg,gmane.ietf.ops
Message-ID <ZR1P278MB11705083FFE0BF2061C9EE1B89FE2@ZR1P278MB1170.CHEP278.PROD.OUTLOOK.COM>
--===============3567560108038137250==
Content-Type: multipart/signed; protocol="application/pkcs7-signature";
 micalg=sha-256;
	boundary="----=_Part_217833_96794165.1783579595390"
Content-Language: en-US

------=_Part_217833_96794165.1783579595390
Content-Type: multipart/alternative;
	boundary="_000_ZR1P278MB11705083FFE0BF2061C9EE1B89FE2ZR1P278MB1170CHEP_"
Content-Language: en-US

--_000_ZR1P278MB11705083FFE0BF2061C9EE1B89FE2ZR1P278MB1170CHEP_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

Dear Joe and Chongfeng,

Catching up on this conversation and thanks for sharing your thoughts and c=
ommenting. What you are describing making very much sense to me. Regarding:

Q4, How does an AI agent interact with Network Digital Twin, Intent-Based N=
etworking, SIMAP, Knowledge Graphs and YANG data in Message Brokers?
  A:   It depends on the specific situation, there should be no one-size-fi=
ts-all solution.

[JMC] See above on a thought on digital twin.  And, yeah, I don't think we'=
ll have a one-size fits all model.

[TG] My biased view is that a Network Digital Twin is helpful in context of=
 Planning & Reasoning where Intent-Based Networking, SIMAP and Knowledge Gr=
aphs in context of Learning & Self-Correction. I see the YANG schema and se=
mantics in the YANG schema registry (https://datatracker.ietf.org/doc/html/=
draft-ietf-nmop-yang-message-broker-integration-13#section-4.4) and in the =
Streaming Catalog (https://datatracker.ietf.org/doc/html/draft-ietf-nmop-ya=
ng-message-broker-integration-13#section-4.5) in Message Brokers as a sourc=
e of information for the RAG (Retrieval-Augmented Generation) and identifyi=
ng from which Message Broker topics which YANG data should be consumed from=
, which Chonfeng lists under Tool Use & Execution.

What are your thoughts? Does that make sense?

Best wishes
Thomas

From: Joe Clarke (jclarke) <[email protected]>
Sent: Thursday, June 25, 2026 8:27 PM
To: Chongfeng Xie <[email protected]>; Graf Thomas, SCS-INI-NET-VNC-E2=
E <Thomas.Graf-Zc0CTiu5wcBWk0Htik3J/[email protected]>; ops-area <[email protected]>; opsawg <opsawg@=
ietf.org>; nmop <[email protected]>; [email protected]
Cc: [email protected]
Subject: Re: [nmrg] Re: [NMOP] Re: [OPSAREA@IETF126] IRTF/IETF OPS Transfer=
: Status & Exploring Collaboration Opportunities

Be aware: This is an external email.

Chongfeng, I mostly agree with everything you said.  That is, I have a simi=
lar understanding.  I do have a few comments, though, based on my implement=
ation experience.


Q1. Which AI agents capabilities are suitable for network management?
   A:   AI agents have the following common capabilities,

    - Perception: Processes multi-modal inputs (text, images, audio) and tr=
acks context and state over time.

[JMC] This depends on model.  Not all models can handle all types of input.=
  And the model capabilities will influence overall cost.

    - Planning & Reasoning: Breaks high-level goals into actionable sub-tas=
ks, dynamically re-plans when obstacles arise, and evaluates trade-offs bef=
ore acting.

    - Tool Use & Execution: Autonomously calls external tools-search engine=
s, APIs, calendars, code interpreters, and databases-to take real action in=
 the digital world (e.g., send emails, book flights, query data).

[JMC] More specifically, with network management, tools can access devices =
to get data and adjust configuration.  In the former, what the agent can th=
en do with the data it retrieves heavily depends on the model and its train=
ing data.  For example, many frontier models generally do well with basic n=
etwork operational data.  Adding on to tool use, RAG or purpose-trained or =
tuned models, and you can get even better results from such tools calls.

    - Learning & Self-Correction: Detects errors, reflects on outcomes, ite=
rates on solutions, and utilizes both short-term and long-term memory to im=
prove over time.

[JMC] This is where Digital Twin comes into place.  You don't necessarily w=
ant a model to "learn" as it's going through your production network.  Test=
ing its "reasoning" in a twin environment makes it safer for doing that sel=
f-correction and iteration.

All the capabilities above are useful for network management. With the unde=
rground support of LLM models, the following functionalities can be realize=
d by AI agents in the context of network management,

   - Intent-based auto-assignment: Automatically routes NOC tickets based o=
n detected intent.

   - Intelligent root-cause analysis: Pinpoints fault origins with precisio=
n.

[JMC] Eh, maybe.  See above.  I've had models go off the rails on hyper-spe=
cific problems where it didn't have a lot of relevant training data.

   - Actionable troubleshooting guidance:  Generates step-by-step plans and=
 recommended resolutions.

   - AI-driven orchestration:  Enables expert-human collaboration and autom=
ated execution of task reassignments/suspensions.

   - Continuous network optimization:  Delivers ongoing tuning recommendati=
ons for wireless, core, and cloud-network resources across diverse scenario=
s.

   - Automated recovery verification:  Validates fault resolution by queryi=
ng network and perceptual metrics via LLM-orchestrated API calls.

Q2. What is the impact of an AI network management process to YANG informat=
ion, service, network and data modelling?
    A:   AI and legcay network management models belong to different domain=
s,  the specific manangement modelling is aganostic to the AI network manan=
gent process. In other words, AI system can process any YANG information, s=
ervice, network and data modelling.

[JMC] This has exactly been my experience.  I've had good luck with a YANG-=
centric skill.  Where things can get problematic is the token consumption X=
ML and JSON produce when using open weight models with tighter context wind=
ows.

Q3.  Is MCP (https://en.wikipedia.org/wiki/Model_Context_Protocol) a suitab=
le protocol between AI agents and IETF network management data sources and =
system components?
     A:  Yes, as an open standard that connects AI models to external data =
and tools, MCP enables AI assistants to securely read files, query database=
s, and execute actions across different applications.  The likelihood of MC=
P being used between between AI agents and IETF network management data sou=
rces and system components is very high.
In addition, other approaches can be used, such as APIs exposed by network =
controller, in this case, AI agents can call the APIs directly for network =
device configuration or data collection.

[JMC] Agree completely.  This does work well.  And MCP has considerable fra=
mework backing.

Q4, How does an AI agent interact with Network Digital Twin, Intent-Based N=
etworking, SIMAP, Knowledge Graphs and YANG data in Message Brokers?
  A:   It depends on the specific situation, there should be no one-size-fi=
ts-all solution.

[JMC] See above on a thought on digital twin.  And, yeah, I don't think we'=
ll have a one-size fits all model.

Joe

--_000_ZR1P278MB11705083FFE0BF2061C9EE1B89FE2ZR1P278MB1170CHEP_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:o=3D"urn:schemas-microsoft-com:office:office" xmlns:w=3D"urn:sc=
hemas-microsoft-com:office:word" xmlns:m=3D"http://schemas.microsoft.com/of=
fice/2004/12/omml" xmlns=3D"http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3D"Generator" content=3D"Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
	{font-family:Aptos;}
@font-face
	{font-family:"Trebuchet MS";
	panose-1:2 11 6 3 2 2 2 2 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0in;
	font-size:12.0pt;
	font-family:"Aptos",sans-serif;}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:#467886;
	text-decoration:underline;}
span.EmailStyle19
	{mso-style-type:personal-reply;
	font-family:"Trebuchet MS",sans-serif;
	color:#0E2841;
	font-weight:normal;
	font-style:normal;}
.MsoChpDefault
	{mso-style-type:export-only;
	font-size:10.0pt;
	mso-ligatures:none;}
@page WordSection1
	{size:8.5in 11.0in;
	margin:70.85pt 70.85pt 56.7pt 70.85pt;}
div.WordSection1
	{page:WordSection1;}
--></style>
</head>
<body lang=3D"DE-CH" link=3D"#467886" vlink=3D"#96607D" style=3D"word-wrap:=
break-word">
<div class=3D"WordSection1">
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US">Dear =
Joe and Chongfeng,<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US"><o:p>=
&nbsp;</o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US">Catching up on this conversation and thanks for sharing your thou=
ghts and commenting. What you are describing making
 very much sense to me. Regarding: <o:p></o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US"><o:p>&nbsp;</o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US">Q4, H=
ow does an AI agent interact with Network Digital Twin, Intent-Based Networ=
king, SIMAP, Knowledge Graphs and YANG data in
 Message Brokers?<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US">&nbsp=
; A:&nbsp; &nbsp;It depends on the specific situation, there should be no o=
ne-size-fits-all solution.<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US"><o:p>=
&nbsp;</o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US">[JMC]=
 See above on a thought on digital twin. &nbsp;And, yeah, I don&#8217;t thi=
nk we&#8217;ll have a one-size fits all model.<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US"><o:p>=
&nbsp;</o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US">[TG] My biased view is that a Network Digital Twin is helpful in =
context of Planning &amp; Reasoning where Intent-Based
 Networking, SIMAP and Knowledge Graphs in context of Learning &amp; Self-C=
orrection. I see the YANG schema and semantics in the YANG schema registry =
(<a href=3D"https://datatracker.ietf.org/doc/html/draft-ietf-nmop-yang-mess=
age-broker-integration-13#section-4.4">https://datatracker.ietf.org/doc/htm=
l/draft-ietf-nmop-yang-message-broker-integration-13#section-4.4</a>)
 and in the Streaming Catalog (<a href=3D"https://datatracker.ietf.org/doc/=
html/draft-ietf-nmop-yang-message-broker-integration-13#section-4.5">https:=
//datatracker.ietf.org/doc/html/draft-ietf-nmop-yang-message-broker-integra=
tion-13#section-4.5</a>) in Message
 Brokers as a source of information for the RAG (Retrieval-Augmented Genera=
tion) and identifying from which Message Broker topics which YANG data shou=
ld be consumed from, which Chonfeng lists under Tool Use &amp; Execution.<o=
:p></o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US"><o:p>&nbsp;</o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US">What are your thoughts? Does that make sense?<o:p></o:p></span></=
p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US"><o:p>&nbsp;</o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US">Best wishes<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span lang=3D"EN-US" style=3D"font-size:10.0pt;font-=
family:&quot;Trebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-langua=
ge:EN-US">Thomas</span><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:gray"><o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:&quot;Tr=
ebuchet MS&quot;,sans-serif;color:#0E2841;mso-fareast-language:EN-US"><o:p>=
&nbsp;</o:p></span></p>
<div>
<div style=3D"border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in =
0in 0in">
<p class=3D"MsoNormal"><b><span lang=3D"EN-US" style=3D"font-size:11.0pt;fo=
nt-family:&quot;Calibri&quot;,sans-serif">From:</span></b><span lang=3D"EN-=
US" style=3D"font-size:11.0pt;font-family:&quot;Calibri&quot;,sans-serif"> =
Joe Clarke (jclarke) &lt;[email protected]&gt;
<br>
<b>Sent:</b> Thursday, June 25, 2026 8:27 PM<br>
<b>To:</b> Chongfeng Xie &lt;[email protected]&gt;; Graf Thomas, SCS-I=
NI-NET-VNC-E2E &lt;Thomas.Graf-Zc0CTiu5wcBWk0Htik3J/[email protected]&gt;; ops-area &lt;ops-area@ietf=
.org&gt;; opsawg &lt;[email protected]&gt;; nmop &lt;[email protected]&gt;; nmrg@=
irtf.org<br>
<b>Cc:</b> [email protected]<br>
<b>Subject:</b> Re: [nmrg] Re: [NMOP] Re: [OPSAREA@IETF126] IRTF/IETF OPS T=
ransfer: Status &amp; Exploring Collaboration Opportunities<o:p></o:p></spa=
n></p>
</div>
</div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<table class=3D"MsoNormalTable" border=3D"0" cellspacing=3D"0" cellpadding=
=3D"0" align=3D"left" width=3D"100%" style=3D"width:100.0%">
<tbody>
<tr>
<td style=3D"background:#CF4A0C;padding:5.0pt 2.0pt 5.0pt 2.0pt"></td>
<td width=3D"100%" style=3D"width:100.0%;background:#FFF8E5;padding:5.0pt 4=
.0pt 5.0pt 12.0pt">
<div>
<p class=3D"MsoNormal" style=3D"mso-element:frame;mso-element-frame-hspace:=
2.25pt;mso-element-wrap:around;mso-element-anchor-vertical:paragraph;mso-el=
ement-anchor-horizontal:column;mso-height-rule:exactly">
<b><span style=3D"color:#222222">Be aware:</span></b><span style=3D"color:#=
222222"> This is an external email.<o:p></o:p></span></p>
</div>
</td>
</tr>
</tbody>
</table>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<div>
<div>
<p class=3D"MsoNormal"><span style=3D"color:black">Chongfeng, I mostly agre=
e with everything you said. &nbsp;That is, I have a similar understanding. =
&nbsp;I do have a few comments, though, based on my implementation experien=
ce.<o:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"color:black"><o:p>&nbsp;</o:p></span>=
</p>
</div>
<div id=3D"mail-editor-reference-message-container">
<div style=3D"border:none;border-top:solid windowtext 1.0pt;padding:3.0pt 0=
in 0in 0in;border-color:currentcolor currentcolor">
<p class=3D"MsoNormal"><span style=3D"color:black"><o:p>&nbsp;</o:p></span>=
</p>
</div>
<div>
<p class=3D"MsoNormal">Q1. Which AI agents capabilities are suitable for ne=
twork management?&nbsp; &nbsp;<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;A:&nbsp; &nbsp;AI agents have the follo=
wing common capabilities,&nbsp;<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; - Perception: Processes multi-modal in=
puts (text, images, audio) and tracks context and state over time.<o:p></o:=
p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] This depends on model. &nbsp;Not all models can hand=
le all types of input. &nbsp;And the model capabilities will influence over=
all cost.<o:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; - Planning &amp; Reasoning: Breaks hig=
h-level goals into actionable sub-tasks, dynamically re-plans when obstacle=
s arise, and evaluates trade-offs before acting.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; - Tool Use &amp; Execution: Autonomous=
ly calls external tools&#8212;search engines, APIs, calendars, code interpr=
eters, and databases&#8212;to take real action in the digital world (e.g., =
send emails, book flights, query data).<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] More specifically, with network management, tools ca=
n access devices to get data and adjust configuration. &nbsp;In the former,=
 what the agent can then do with the data it retrieves
 heavily depends on the model and its training data. &nbsp;For example, man=
y frontier models generally do well with basic network operational data. &n=
bsp;Adding on to tool use, RAG or purpose-trained or tuned models, and you =
can get even better results from such tools
 calls.<o:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; - Learning &amp; Self-Correction: Dete=
cts errors, reflects on outcomes, iterates on solutions, and utilizes both =
short-term and long-term memory to improve over time.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] This is where Digital Twin comes into place. &nbsp;Y=
ou don&#8217;t necessarily want a model to &#8220;learn&#8221; as it&#8217;=
s going through your production network. &nbsp;Testing its &#8220;reasoning=
&#8221; in a twin
 environment makes it safer for doing that self-correction and iteration.<o=
:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">All the capabilities above are useful for network ma=
nagement. With the underground support of LLM models, the following functio=
nalities can be realized by AI agents in the context of network management,=
<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; &nbsp;&nbsp;<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;- Intent-based auto-assignment: Automat=
ically routes NOC tickets based on detected intent.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;- Intelligent root-cause analysis: Pinp=
oints fault origins with precision.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] Eh,
<i>maybe</i>. &nbsp;See above. &nbsp;I&#8217;ve had models go off the rails=
 on hyper-specific problems where it didn&#8217;t have a lot of relevant tr=
aining data.<o:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;- Actionable troubleshooting guidance:&=
nbsp; Generates step-by-step plans and recommended resolutions.<o:p></o:p><=
/p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;- AI-driven orchestration:&nbsp; Enable=
s expert-human collaboration and automated execution of task reassignments/=
suspensions.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;- Continuous network optimization:&nbsp=
; Delivers ongoing tuning recommendations for wireless, core, and cloud-net=
work resources across diverse scenarios.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;- Automated recovery verification:&nbsp=
; Validates fault resolution by querying network and perceptual metrics via=
 LLM-orchestrated API calls.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp;&nbsp;<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">Q2. What is the impact of an AI network management p=
rocess to YANG information, service, network and data modelling?<o:p></o:p>=
</p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; A:&nbsp; &nbsp;AI and legcay network m=
anagement models belong to different domains,&nbsp; the specific manangemen=
t modelling is aganostic to the AI network manangent process. In other word=
s, AI system can process any YANG information, service, network
 and data modelling.&nbsp;&nbsp;<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] This has exactly been my experience. &nbsp;I&#8217;v=
e had good luck with a YANG-centric skill. &nbsp;Where things can get probl=
ematic is the token consumption XML and JSON produce when using
 open weight models with tighter context windows.<o:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">Q3.&nbsp; Is MCP (<a href=3D"https://en.wikipedia.or=
g/wiki/Model_Context_Protocol">https://en.wikipedia.org/wiki/Model_Context_=
Protocol</a>) a suitable protocol between AI agents and IETF network manage=
ment data sources and system components?<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; &nbsp; &nbsp;A:&nbsp; Yes, as an open standar=
d that connects AI models to external data and tools, MCP enables AI assist=
ants to securely read files, query databases, and execute actions across di=
fferent applications.&nbsp; The likelihood of MCP being used
 between between AI agents and IETF network management data sources and sys=
tem components is very high.&nbsp;<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">In addition, other approaches can be used, such as A=
PIs exposed by network controller, in this case, AI agents can call the API=
s directly for network device configuration or data collection.&nbsp;<o:p><=
/o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] Agree completely. &nbsp;This does work well. &nbsp;A=
nd MCP has considerable framework backing.<o:p></o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal">Q4, How does an AI agent interact with Network Digit=
al Twin, Intent-Based Networking, SIMAP, Knowledge Graphs and YANG data in =
Message Brokers?<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal">&nbsp; A:&nbsp; &nbsp;It depends on the specific sit=
uation, there should be no one-size-fits-all solution.<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">[JMC] See above on a thought on digital twin. &nbsp;And, y=
eah, I don&#8217;t think we&#8217;ll have a one-size fits all model.<o:p></=
o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black"><o:p>&nbsp;</o:p></span></p>
</div>
<div>
<p class=3D"MsoNormal"><span style=3D"font-family:&quot;Arial&quot;,sans-se=
rif;color:black">Joe<o:p></o:p></span></p>
</div>
</div>
</div>
</div>
</body>
</html>

--_000_ZR1P278MB11705083FFE0BF2061C9EE1B89FE2ZR1P278MB1170CHEP_--

------=_Part_217833_96794165.1783579595390
Content-Type: application/pkcs7-signature; name=smime.p7s; smime-type=signed-data
Content-Transfer-Encoding: base64
Content-Disposition: attachment; filename="smime.p7s"
Content-Description: S/MIME Cryptographic Signature
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------=_Part_217833_96794165.1783579595390--


--===============3567560108038137250==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: base64
Content-Disposition: inline

X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KT1BTQVdHIG1h
aWxpbmcgbGlzdCAtLSBvcHNhd2dAaWV0Zi5vcmcKVG8gdW5zdWJzY3JpYmUgc2VuZCBhbiBlbWFp
bCB0byBvcHNhd2ctbGVhdmVAaWV0Zi5vcmcK

--===============3567560108038137250==--