MCP in Mist

Exchanging context has always been a critical pillar of networking. Exchanging routes, synchronizing tables, building trees, there are many different networking protocols and frameworks that have been defined and refined over the years intended to make sure that data is flowing freely. What if we had a way to exchange intelligence between systems similar to […]

Mist Telemetry

The Mist dashboard contains a lot of valuable information and insights for network automation, troubleshooting, and debugging. It can also be extended into other IT systems through the usage of the extensive webhook, websocket, and API systems available within Mist. Every single action in the GUI has a corresponding API call. The first part of […]

DIY AGENTIC AI

Like many of you who have been in tech for a while, I keep a pretty hefty private wiki with all the lessons I’ve learned and the platforms I’ve worked with over the years. My database contains thousands of pages – not all of them useful, mind you – and it spans topics ranging from […]

PCAPs and PANDAS

In a previous post I reviewed how you can use EDA techniques to programmatically pull data from the Mist dashboard for large-scale analysis. But what if you don’t have access to the Mist dashboard – or if you need to work with a raw PCAP that has been provided? Packets don’t lie but a picture […]

Learning ML

Or, in other words, learning how to learn how machines are learning. I’ve spent the last two years going on a self-guided learning journey to better understand AI/ML and how it can be creatively applied to the networking field. There are some great resources out there …. but there are also a LOT of resources […]

Networking EDA

Interesting in troubleshooting your network programmatically? One of the more valuable things I’ve learned while brushing up on AI/ML is exploratory data analysis (EDA) techniques. Here’s an example of using Jupyter notebooks and API calls to slice and dice through your production data to help make informed decisions. Problem Statement:A critical class of network clients […]

TROUBLESHOOTING W/ ML:

One of my favorite components of the Mist platform is the microservices architecture running underneath the hood. This architecture brings a lot of operational advantages – resiliency, stability, speed, scale – and it brings new features into the dashboard on a regular basis. Earlier this week we launched a new feature that I’ve been watching […]

UNCOVERING COVERAGE TRENDS WITH ML:

For this post I will show you an example of how you can use ML to determine common characteristics seen by clients experiencing poor coverage in your WLAN. I want to note upfront that this is a science project intended to illustrate the inner workings of a machine learning algorithm, not a cure for poor […]

AI/ML FOUNDATIONS IN NETWORKING:

It has been a while! I’ve spent the past year or so diving deep into AI/ML techniques – learning about what’s actually happening under the hood with these different algorithms and determining what they can (and can’t) accomplish in the networking world. This personal learning journey culminated in an intensive twelve-week program with MIT on […]

mist webhooks

One of the most personally intriguing features to me within the Mist platform is the level of programmability that is available. You can accomplish most tasks through the Mist GUI if you wish … from architecting and pushing out configuration templates all the way down to writing queries to sift through the sea of data […]