Engineering Agentic Network Operations

This live online workshop is designed for network engineers and automation practitioners who want to move beyond AI experimentation and start building reliable, production-minded agentic workflows for network operations.

Engineering Agentic Network Operations reintroduces AI tooling, this session focuses on the engineering discipline required to make AI agents practical in real-world environments. Participants will learn how to move from raw MCP tools to structured skills, apply spec-driven development to define and constrain agent behavior, design agentic loops that recover safely when things go wrong, and work with OpenClaw and NetClaw as production-ready frameworks for network automation.

Delivered as a virtual, hands-on workshop with live instruction, this event combines demonstrations, guided exercises, and practical labs across a modern AI networking stack including MCP, OpenClaw, NetClaw, Python, Claude, Selector AI, and Containerlab. It is intended for practitioners who have already built or used an MCP server and are comfortable with Python, CLI workflows, and basic AI tooling.

What makes this workshop different?

This workshop stands out because it goes deeper than introductory AI-for-networking sessions and focuses on the real design challenges behind usable agent systems.

Participants will benefit from:

• A direct follow-up to the first Build Intelligent Networks with AI workshop

• Two instructors with complementary perspectives: engineering discipline and framework-led implementation

• Practical exposure to OpenClaw and NetClaw as working frameworks, not just ideas

• A strong emphasis on spec-driven development as an engineering discipline

• Honest treatment of agentic loop failure, including recovery patterns and safe handoff design.

What you’ll learn

By the end of the workshop, participants will be able to:

• Explain how MCP skills differ from raw tool exposure and when to use each

• Build MCP skills that are composable, reusable, and appropriately scoped

• Apply spec-driven development to define and constrain agent behavior

• Design agentic loops that detect when they are stuck and recover or hand back control

• Deploy and extend OpenClaw and NetClaw for network-specific agentic workflows

• Integrate AI-driven observability using Selector AI for real operational context.
  

Who Is This Workshop For

This workshop is designed for network professionals who want to bring the power of AI into their daily workflows. It’s perfect for those ready to move beyond theory and apply AI to real-world network operations using open-source tools and live lab environments.

Who Should Attend

• Network Engineers and Architects with 3 to 10 years of experience who want to modernize their approach to automation and observability.

• Automation and DevOps Engineers familiar with CLI, Ansible, or Git who are ready to experiment with AI copilots for faster, smarter development.

• Operations and Platform Teams seeking to deploy AI-powered monitoring, alert summarization, and troubleshooting solutions.

• Technical Leads and Infrastructure Managers guiding network or automation projects who want to understand the capabilities and limitations of AI-driven operations.

Event format

• Format: Online live workshop

• Duration: 4 hours

• Working time: 3.5 hours plus breaks

• Level: Intermediate to advanced

• Style: Hands-on, live instruction, practical lab-based learning.

Technologies covered:

Participants will work with MCP, OpenClaw, NetClaw, Python, Claude, Selector AI, Containerlab, plus supporting tools used throughout the labs such as the MCP Python SDK, FastMCP, Gridctl, and Arista cEOS.