JOHN CAPOBIANCO / GOOGLE DEVELOPER EXPERT

Build. Share.
Make it possible.

My work as a Google Developer Expert in Cloud AI and Google Cloud: connecting Gemini, agents, and real networks—and sharing what I learn along the way.

GDE SINCE FEBRUARY 12, 2026

The work behind
the recognition.

I report my community contributions in Advocu: educational videos and podcasts, practical articles, conference talks, hands-on workshops, mentoring, and open-source projects.

Advocu may require a GDE community sign-in. The original work is available through the links here.

How to build a custom vision agent — Google Cloud Tech video thumbnail
FEATURED WITH GOOGLE / GOOGLE CLOUD TECH

How to build a custom vision agent.

Join me on Google Cloud Tech to build with Gemini and MCP: camera input, image generation, video, and an agent that can see.

BUILD WITH ME / OPEN SOURCE

Explore the code.

All projects ↗

28 repositories from my GitHub collection. Forks and archived projects are labeled.

HTML

kagent_vision

A KAgent Agent with Vision - Capture photos, transform them with Nano Banana, animate them with Veo3. Supports ASL.

JavaScript

google_drone

100% vibe coded Google Drone using Google Maps SDK / MCP; Vision Extension; Computer Use extension from just prompts

Python

VibeGraphics

An MCP Server / Gemini CLI Extension to create modern Infographics for your project - VibeGraphics - Generated with Nano Banana and animated with Veo3

PythonFORK

A2A

An open protocol enabling communication and interoperability between opaque agentic applications.

HTML

Modern_Show_Version

Cisco IOS-XE Show Version Command Reimagined as a pyATS job that creates CSV / MD / HTML; sends #chatbot messages; and generates MP3 using Google Cloud TTS #voice

DEMOS / TUTORIALS / LIVE BUILDS

Gemini, agents, and experiments.

Full video library ↗

53 videos

FROM THE WORKBENCH

Writing & posts.

Recent workshops, open-source releases, AI governance conversations, and practical tutorials, alongside my Gemini and Google experiments. These are my independent contributions; each article states its tested scope.

AIOct 30, 2026

Building With Lumen: Engineers, FlowAgents, and a Summit Full of Ideas

Photos and reflections from Lumen’s October Innovation Summit: hands-on FlowAI workshops, Greg Freeman’s recap, Marc Montez on trust, and my full Itential write-up.

2 MIN READ
NetClawOct 30, 2026

Fourteen Ways to Build the Testbed: Dynamic Source Composition in NetClaw

Part two: NetClaw 1.14.0 brings static/dynamic testbed choice, fourteen source routes and reviewed pyATS activation to its VS Code and terminal installers.

7 MIN READ
NetClawOct 30, 2026

NetClaw on Heavy Networking: An Open Source Network Assistant

Back with Ethan Banks and Drew Conry-Murray on Packet Pushers to talk NetClaw: MCP, explicit approvals, layered protection, federation, and the community building it.

2 MIN READ
NetClawOct 30, 2026

From a Converted Configuration to a Migration You Can Test

How NetConverter and NetClaw can connect reviewed conversion artifacts with virtual-target rehearsals, validation and change evidence. Live conversion qualification is pending.

4 MIN READ
Network automationOct 30, 2026

The Testbed Becomes Part of the Conversation: Dynamic Inventory in pyATS MCP

Part one: pyATS MCP can build an in-memory testbed from inventory systems and structured data, then make it available to its existing network automation tools.

5 MIN READ
AIOct 29, 2026

Learning in Public: Elliot Conner in the VibeOps Lounge

VibeOps Lounge 007: Elliot Conner brings a Containerlab operations dashboard, an AI network planner, and a troubleshooting game to a conversation about learning by building.

2 MIN READ
AIOct 16, 2026

Two Network Geeks, One Table: Eva Santos in the VibeOps Lounge

From Walmart freight to CWNE #521: Eva Santos joins me to talk Wireshark, ChromeOS Wi-Fi Fixer, Claude Code, and building useful tools before the token buffet closes.

5 MIN READ
AIOct 14, 2026

Back on The Cloud Gambit: MCP, NetClaw, and AI Governance

My conversation with William Collins on Packet Pushers: MCP in production, NetClaw’s constitution, human oversight, model identity, and specialized decision models.

4 MIN READ
NetClawOct 14, 2026

From an Ubuntu CD to the Agentic AI Foundation

Twenty-one years after a free Ubuntu CD got me started, the Linux Foundation’s Agentic AI Foundation (AAIF) is publishing my MCP and NetClaw story. A personal honour and a milestone for the project and its community.

2 MIN READ
NetClawOct 11, 2026

NetClaw Comes to Visual Studio Code

A network operations workbench beside your code: NetClaw brings Chat, Canvas, RAG, Testbed management, per-MCP setup and reviewed security controls into Visual Studio Code.

11 MIN READ
AIOct 10, 2026

Good Friends, Systems Thinking, and a Hello World for AI

Andy Lapteff and Ryan Booth talk AI, systems thinking, and the future of network engineering—and revisit my Hello World for AI session and our subnetting game.

4 MIN READ
NetClawOct 10, 2026

Good news for Hermes users!

NetClaw 1.8.0 brings protected Hermes federation and Mobile Ask Border together, following the shared HUD work in 1.7.0. Five diagrams explain the design and its tested boundaries.

6 MIN READ
AIOct 10, 2026

Life Before AI: The Merlin Years

86,688 lines of hand-written code, about 550 hours, and the Django detour that helped me build NetworkGPT in two weeks. What Merlin taught me—and permission to build differently now.

12 MIN READ
NetClawJul 12, 2026

NetClaws, Assemble: introducing N2N Federation and the NCFED protocol

NetClaw’s mesh could always tell you who was online. Now it tells you what they can do — and lets you use it. Introducing N2N Federation and NCFED, a new protocol for federating AI network engineers safely.

12 MIN READ
NetClawFeb 20, 2026

8 hours of netclaw – by netclaw

We Gave a Slack Channel Full of Engineers an AI Network Agent. Here’s What Happened. A live red-team session, a VASI BGP lab, and 30+ social engineering attempts — all in one Friday afternoon. ─── The Setup The premise was simple: drop an A

7 MIN READ
AnsibleMar 7, 2021

My Network Talks To Me – Literally!

This next post may seem like science fiction. I woke up this morning and checked that my output files – MP3 files – really did exist and that I actually made my Cisco network “talk” to me! This post is right out of Star Trek so strap yourse

10 MIN READ
OCTOBER 2026 / PUBLISHED ELSEWHERE

More writing from the community.

Original articles on Itential, the Agentic AI Foundation, and LinkedIn, with their publication dates and publisher attribution.

DevOps.comArticle

Your AI Agent Needs an Operating Environment. Who’s Engineering It?

John explains why infrastructure agents need scoped tools, current context, enforced approvals, and evidence of completion, and why engineers must own and test the operating environment around the model.

OPEN ORIGINAL
ItentialArticle

Inside Lumen’s Innovation Summit: 40 Agents in 45 Minutes With Itential FlowAI

John’s field report from Lumen’s hands-on FlowAI workshops, including session outcomes, inherited workflow documentation, and human-approved agent coordination.

OPEN ORIGINAL
ItentialArticle

Jev Told My FlowAgents to Roll Back. I Kept That in the Demo.

A demonstration of decision gates, scoped tools, human approvals, and recovery: Claude coordinates, Jev evaluates evidence, and Gemma handles reporting.

OPEN ORIGINAL
LinkedInArticle

The Network Engineer Who Hates Programming Just Built an App

John follows Andy Lapteff’s public learning journey from initial AI experiments to building an app, with links to their conversations and demonstrations.

OPEN ORIGINAL
LinkedInArticle

The Prisoner's Dilemma of Network Automation and AI Adoption

John uses the prisoner’s dilemma as a lens for discussing individual incentives, shared learning, and AI adoption among network engineers.

OPEN ORIGINAL
Agentic AI Foundation (AAIF)Article

I Saw Something in MCP. Then I Spent 18 Months Building It.

John Capobianco’s MCP and NetClaw story, published October 14, 2026 on the official blog of the Linux Foundation’s Agentic AI Foundation. A personal honour and a milestone for the NetClaw project and community.

OPEN ORIGINAL
ItentialArticle

Why Determinism Is the Key to Safely Running AI Agents in Network Operations

Why infrastructure operations need repeatable execution around probabilistic reasoning, and where governed workflows fit into agent-driven changes.

OPEN ORIGINAL
ItentialArticle

MCP Connects the Agent. What Governs the Change?

John’s Toronto reflections on tool access, identity, permissions, and the operational controls needed when MCP-connected agents can change infrastructure.

OPEN ORIGINAL