Start hereBuilt for operators
The resource pantry
Pick the format that fits the job.
Read a field note, follow a how-to, fork a repo, or grab a runbook when the system is wobbling.
Field notes from the working kitchen
Practical AI for MSPs
Field-tested articles, honest conversations, free tools, practical guides, and operator-ready runbooks for MSP teams building with AI.
The full menu
Choose the way you want to learn.
Short on hype. Heavy on materials you can use with your team, your clients, and your actual technology stack.
01Field notes
Blog
What survives contact with an MSP.
Honest lessons, working patterns, and strong opinions from building AI inside a managed service provider.Open the section
02Operator conversations
Podcast
The conversations that don’t fit in a slide deck.
Practical conversations about the use cases, failures, tradeoffs, and decisions behind AI in the MSP world.Open the section
03Free GitHub repos
Repos
Fork it. Break it. Make it fit your stack.
Starter kits, utilities, templates, and reference implementations built to be understood—not treated like black boxes.Open the section
04Task-based instructions
How-To
One task. Clear steps. No mystery meat.
Focused walkthroughs with the exact steps, commands, checks, and decisions needed to finish a specific job.Open the section
05Start-to-finish guidance
Guides
From blank page to working practice.
Deeper guidance for shaping an AI strategy, building the capability, and operating it responsibly at an MSP.Open the section
06Operator-ready procedures
Runbooks
When the system is wobbling, start here.
Practical response procedures for incidents, rollbacks, governance failures, and model or provider outages.Open the section
07Learn with other operators
Community
MSP operators learning in public.
A place for peer learning, office hours, practical reviews, and candid discussion about putting AI to work.Open the section
Before you start
AI mise en place.
Three ingredients we keep on the counter for every AI project.
- 1
Begin with real work
Find the frustrating workflow before reaching for the newest model.
- 2
Keep a human in the kitchen
Build judgment, review, and accountability into the way the tool is used.
- 3
Measure the meal
Decide what better looks like, then check whether you actually made it.
On the editorial prep list
First field notes.
The honest version of building AI at an MSP—decisions, mistakes, and what holds up in production. We’ll link these here when they are ready.
From the field
The demo is not the product
Strong opinion
Your AI policy should help people say yes
What we learned
Start with the workflow, not the model
Why Cooking Up AI?
We’re building this in the real world, not a lab.
We’re Anthony Latham and Graham Rosenberg—two Sourcepass operators working through the practical questions that appear when AI moves from slide decks into service delivery.
This is where we’ll share the articles, conversations, code, guides, and runbooks we wish we had when we started. Everything is for people with clients to serve, teams to support, and no appetite for empty hype.
Meet the people in the kitchen →