Blog
Notes from the workbench.
Plain-language notes from Miro on AI, automation and keeping both under a person's control. The free video lessons are on YouTube; the written notes are here.
-
Why every workflow I ship pauses for a human
The one rule behind everything on this site, where it came from, and how to add it to a workflow in five minutes.
-
Who I am, and what I actually do all day
I run infrastructure for a cloud host by day and a handful of small businesses on the side. ATLAS Academy is me writing down what works, in the order I wish someone had shown me.
-
Where AI is going, and what's actually worth learning right now
No predictions about robots. What has changed in the last two years from where I sit, what I think holds, and the three skills I'd spend time on if I were starting today.
-
Machine learning, deep learning and generative AI, explained the way I wish someone had explained it to me
Three terms that get used interchangeably and mean different things. One picture, no math, and the part that actually matters when you're deciding what to automate.
-
How a lesson gets made (and why they're slow on purpose)
The result-first opening, the pauses that give you time to try each step, the AI voice, and the automatic checks every lesson passes before it goes live.
-
The ways AI gets attacked, and how to protect yourself and your business
I run infrastructure for a living, so I think about this a lot. The real risks — prompt injection, over-permissioned agents, data leaks, deepfake scams — and the plain fixes for each.
No post matches that yet. Try a shorter search, or the free lessons.
Free lessons
Latest from the channel
The newest free lessons, each with its own lesson page. Subscribe on YouTube
-
Self Host n8n with Docker for Beginners (Free, Step by Step)
n8n Workflows from Zero
-
Ollama vs llama.cpp vs vLLM vs NIM vs TensorRT-LLM on DGX Spark
Local AI
-
Build a Custom Claude Connector: a Remote MCP Server with OAuth (Beginner Guide)
Claude Mastery
-
Add Email as a Second Channel to Your Claude + n8n Assistant
Claude + n8n Project
-
Run Hermes Agent on DGX Spark with vLLM (Following NVIDIA's Playbook)
Local AI
-
n8n Webhooks and APIs Deep Dive: Connect Any App
n8n Workflows from Zero
Ticks are kept only in this browser, on this device.
The pictures here are served by this store. Nothing loads from YouTube until you open a lesson and press play.