Comments for {networkphil}

Comment on Understanding the A2A Protocol for Agentic AI in Network Operations by Phil Gervasi

Phil Gervasi — Mon, 02 Mar 2026 21:00:31 +0000

That’s a great point! I think the issue will be more on the interpretation side than the retrieval of metrics side so long as we take certain precautions. One thing is that data that’s stored in the artifact has appropriate source metadata like source of the telemetry, the query that was used, timestamp, etc). Another idea would be to not allow the RCA agent to advance to diagnosis until the necessary artifacts exist in the first place.

And one thing that I’m seeing folks do right now is make sure that any factual statement returned by the system has to reference the actual source information in some way, whether it’s the artifact or just a list of sources. And if a result is generated without the sources, the task can’t proceed and alerts a person. That means you’d need to add a human-in-the-loop as a check.

The steps I put in the blog were pretty high level to help folks get an understanding of a basic workflow, but verification gates at specific points would definitely be a good idea.

LikeLike

Comment on Understanding the A2A Protocol for Agentic AI in Network Operations by nhoward92

nhoward92 — Mon, 02 Mar 2026 18:55:39 +0000

Great walkthrough, Phil. The A2A + MCP separation is the right architecture — horizontal agent collaboration plus vertical tool access. One piece I think is missing from the stack: observation verification. In your Step 2, how does the RCA Agent know the Telemetry Agent’s data is real? I ran into this firsthand building a multi-vendor AI ops platform. The AI fabricated three firewall policies that didn’t exist on my FortiGate — among a lot of other data when it wasn’t presented with expected output. It guessed the next most plausible response, which meant hallucinating perfectly formatted, convincing output to the user. Passed every sanity check. Just weren’t real. I’m building a protocol layer (VIRP — Verified Infrastructure Response Protocol) that sits at the MCP boundary and cryptographically signs device observations so agents can prove their data came from the actual device, not from hallucination. The way I think about it: A2A = agent-to-agent, MCP = agent-to-tool, VIRP = tool-to-truth. Would love to compare notes — our work is complementary.

LikeLike

Comment on A Network Engineer’s Guide to Understanding the Model Context Protocol for AI Integration by Understanding the A2A Protocol for Agentic AI in Network Operations – {networkphil}

Mon, 02 Mar 2026 16:43:53 +0000

[…] is all about agent-to-agent communication, like its name suggests. MCP, on the other hand, is about agent-to-tool communication. MCP is how agents call tools like NetFlow […]

LikeLike

Comment on Beginner’s Guide for Using Large Language Models in Network Operations by Sean Mahoney

Sean Mahoney — Fri, 22 Nov 2024 01:03:33 +0000

This was excellent!

thank you

LikeLiked by 1 person

Comment on Deploying and Configuring the Cisco 9800 Virtual Wireless Controller for the First Time by Devin Akin

Devin Akin — Sat, 28 Oct 2023 17:07:13 +0000

This blog saved me. Thank you. The ESXi settings were the key to getting it working. I really appreciate you taking the time to write this!

LikeLike

Comment on 10 Networking Tools to Keep in Your Bag by Aidan

Aidan — Fri, 22 Sep 2023 10:37:08 +0000

Handy list. Is there a wireless console cable you’d recommend? I’ve seen airconsole but see very mixed reviews

Thanks

LikeLike

Comment on BGP Default Route Failover Using Reachability by Masterful Technique | Technology as Nature

Masterful Technique | Technology as Nature — Mon, 05 Jun 2023 09:46:19 +0000

[…] when I depart is that I can be schmoozing with clients one day, putting them at ease, and setting BGP failover the […]

LikeLike

Comment on Networking is Finally Catching Up by Lance I

Lance I — Sun, 08 Jan 2023 12:04:46 +0000

Greaat read thanks

LikeLike

Comment on Top 7 Network Engineering Conferences Ranked by Top 7 Network Engineering Conferences Ranked - Tech Field Day

Top 7 Network Engineering Conferences Ranked - Tech Field Day — Wed, 16 Nov 2022 15:20:04 +0000

[…] Top 7 Network Engineering Conferences Ranked […]

LikeLike

Comment on Top 7 Network Engineering Conferences Ranked by Brandon R

Brandon R — Thu, 03 Nov 2022 02:12:29 +0000

“One of the real beauties of NFD is that the presenters know (most of the time) that the delegates are there for deep, hard-hitting technical content without any marketing fluff. It forces vendors to cut to the chase, keep it real, and just present their technology for what it is. That’s a big deal to me.“

Very well said!

LikeLiked by 1 person