LIVE · 4-HOUR HANDS-ON WORKSHOP

Engineering Agentic Network Operations

A hands-on Packet Coders workshop. Engineer an AI agent with the P.E.N.E. framework to build read-only, MCP-exposed network tools to safely troubleshoot networking issues.

Sif Baksh
Your instructor Sif Baksh · Principal Systems Engineer, Tines
Date Tue 28 Jul 2026
Time 16:00–20:00 BST · 11:00–15:00 EST
Length 4 hours
Level Intermediate

Live session + lifetime recording · Full workshop repo · Limited seats

agent · network-ops
$ agent run "check leaf1 - anything wrong?"

 list_devices()              [read-only]
 get_device_facts(leaf1)      [read-only]
 check_interfaces(leaf1)      [read-only]
 check_bgp_neighbors(leaf1)   [read-only]

 Ethernet3 - down
 BGP 10.0.0.5 - state = Active

 Likely cause: Ethernet3 down →
  BGP session not established.
  No changes made - next check ready.

AI agents are everywhere. For network engineers the real question isn't "what is an agent?" - it's "how do I safely use one to build useful network automation?"

This is not a hype session. It is not "let the chatbot fix the network." It's a practical, hands-on workshop for engineers who want to understand how AI coding agents actually fit into network operations.

What you'll build

A working AI-assisted troubleshooting workflow

You leave with something real - not a demo. Across the session you'll build, piece by piece:

A network lab using Arista cEOS
A structured device inventory
An AI-generated Python inventory loader
Read-only device inspection tools
Interface and BGP troubleshooting functions
A Claude / OpenAI reasoning layer
A prompt workflow using the P.E.N.E. framework
An MCP server exposing approved network tools
A final troubleshooting agent workflow
Tests and guardrails for safer AI-generated automation

Ask: "Can you check leaf1 and tell me if anything looks wrong?"

Discover devices Collect facts Check interfaces Check BGP Analyze evidence Recommend next check

The agent can inspect, summarize and recommend - it works only from evidence collected by the tools you approved. It cannot change the network.

What you'll learn

The most important thing isn't a tool - it's the workflow: prompt → generate → review → run → test → improve → expose.

Generate code with agents

Use AI coding agents to write network automation, with prompts and the P.E.N.E. framework that produce useful, specific code.

Review for risk

Read AI-generated code like a senior engineer - spotting unsafe commands, hardcoded secrets and weak error handling before you run it.

Test & debug

Run generated Python, capture runtime errors and feed them back to the agent to improve the code, test-driven.

Build read-only tools

Add safety constraints and build read-only troubleshooting tools - avoiding dangerous generic command-execution patterns.

Expose tools with MCP

Expose only narrow, approved functions through MCP - and understand why a generic run_command tool is dangerous.

Reason over evidence

Use Claude or OpenAI (BYOK, with a mock-mode fallback) as a reasoning layer over collected evidence - not as a source of truth.

Agenda

Four hours, nine modules

Learn by doing. Hands-on AI network automation, built live.

0:00–0:20

1 · Welcome & big picture

Chatbots vs scripts vs copilots vs agents - why agents need tools, why the engineer stays critical, and the workshop's safety model.

0:20–0:45

2 · Lab setup & environment

Repo, Python venv, Docker and an Arista cEOS topology. BYOK API setup with a mock-mode fallback.

0:45–1:10

3 · Agent context & safety

Write an agent context file: the lab, repo, devices, allowed commands and read-only boundaries - approved vs unsafe tool patterns.

1:10–1:40

4 · Agent builds the inventory loader

Prompt the agent for a real first component - validating YAML, returning structured data and clear errors. inventory_loader.py

1:40–2:15

5 · Agent builds read-only network tools

Live device inspection: SSH, read-only show commands, structured JSON.

2:15–2:25

Break

2:25–2:55

6 · Review, debug & improve

Review generated code like a senior engineer, run it, capture errors and feed them back. Test-driven improvement and guardrails.

2:55–3:20

7 · Add the reasoning layer

Send structured network data to Claude/OpenAI to summarize, identify causes and recommend the next safe check - evidence-based, not hallucinated.

3:20–3:45

8 · Expose approved tools with MCP

Register narrow, approved, read-only functions as MCP tools - and why a generic run_command tool is dangerous.

3:45–4:00

9 · Final troubleshooting agent demo

Bring it together: the agent uses approved tools, collects evidence and returns a grounded recommendation - without touching config.

Who it's for

You don't need to be an advanced Python developer - just comfortable with basic networking, the CLI, and reading simple code.

Automation engineers using AI coding tools more effectively.
Network engineers who want to understand AI agents.
DevNet engineers exploring MCP.
NetOps teams evaluating AI-assisted troubleshooting.
Engineers who know some Python but want a practical AI workflow.
Technical leaders who want their teams using AI safely, not randomly.

What's included

A complete workshop repo to keep

You're not just leaving with a demo - you're leaving with a reusable pattern you can keep learning from after the session.

Full 4-hour walkthrough & episode-style labs
Student setup guide
Arista cEOS lab topology & configs
Python starter & solution code
Prompt library
Claude/OpenAI BYOK setup & mock-mode fallback
MCP server implementation
Example outputs, tests & safety checks
Troubleshooting guide
Sif Baksh

Your instructor

Sif Baksh

Principal Systems Engineer, Tines

Sif Baksh is a Principal Systems Engineer at Tines with more than 15 years of experience in network automation and cybersecurity. Previously at Swimlane and Infoblox, he helps NetOps and SecOps teams design scalable, resilient automation. Sif is also a technical blogger and volunteer cybersecurity educator.

FAQs

Do I need to know Python?+

You should be able to read basic Python, but you don't need to be an advanced developer. Part of the workshop is learning how to guide an AI coding agent to generate useful Python, then review and test it safely.

Do I need an API key?+

Bring your own Claude or OpenAI API key for the live LLM portions. The workshop supports Claude, OpenAI and mock mode - if you don't have a key, you can still complete the labs using mock mode.

Will the AI make changes to the network?+

No. The workshop uses a read-only safety model. The agent can inspect devices, collect facts, check interface and BGP state, summarize evidence and recommend next checks - it cannot make configuration changes.

Why use MCP?+

MCP gives a clean way to expose approved tools to an agent. Instead of arbitrary commands, you expose specific functions like check_interfaces, check_bgp_neighbors and get_device_facts - safer, easier to test and easier to explain.

Why not just give the agent a generic run command?+

Because that gives the agent too much power and quickly becomes unsafe. This workshop teaches you to expose narrow, approved, read-only tools instead.

Can this work with other vendors?+

Yes. We use Arista cEOS because it's practical for labs, but the same pattern adapts to Cisco, Juniper, Palo Alto, Fortinet, F5, NetBox, Nautobot, Infoblox, Meraki and more: approved tools + structured context + human review + MCP exposure + evidence-based reasoning.

What's the main takeaway?+

AI doesn't replace the network engineer. The engineer becomes the architect, reviewer, tester and safety gate. The agent helps generate code and reason over evidence - but the engineer defines what gets built, what's safe, and what gets exposed.

Reserve your seat

Four hours live, the full workshop repo, and a reusable pattern you'll apply to every agent you build after.

4-hour live, hands-on build with Q&A
Lifetime access to the recording
Full repo: labs, starter & solution code, prompt library, MCP server
Bring your own Claude/OpenAI key - or use mock mode
Early bird · save 25%
$262 $350 one-time
CodeEARLYBIRDAI

Early-bird price expires in 7 days · 7 Jul 2026

Tue 28 Jul 2026

16:00–20:00 BST · 11:00–15:00 EST · 08:00–12:00 PDT · 17:00–21:00 CEST

Limited seats remaining

Can't make it live? Register anyway - you'll get the full recording.