Lernreise

5 min read

Lernreise 7/7: n8n, a Dead ThinkPad, and What's Next

Every project like this ends with a set of opinions you did not have before. Here are mine. n8n I will be charitable and say: n8n is excellent for linear workflows of three to five nodes. Trigger, action, done. For anything more complex, it becomes something I would describe, with some restraint, as binary toxic waste. Visual workflow tools have an inherent problem: the visual representation is the code. You cannot refactor it the way you refactor code. You cannot diff it sensibly. You cannot review it in a pull request. When a node is producing wrong output and you need to understand why, you are clicking through a canvas, unfolding nested expressions, reading JavaScript embedded in a UI field that was not designed to hold much JavaScript.

lernreise ai n8n lessons-learned homelab
4 min read

Lernreise 6/7: What AI Actually Can (and Cannot) Do

I want to write this post carefully, because the nuance matters and most things written about AI productivity are not careful. The AI tools I used this week were remarkable and frustrating in roughly equal measure, at different times, for different reasons. Both things are true. Neither cancels the other. Start with the remarkable. The wiki documentation was worth the experiment on its own. Every piece of infrastructure I provisioned, every workflow component I built, ended up documented in the Gitea wiki in language that a human could read and learn from. Not command logs. Actual explanations: what was built, why this approach was chosen, what to watch out for. This is documentation that would never have existed if I had done the work alone, because I am the kind of person who documents things enthusiastically on day one and then never again.

lernreise ai lessons-learned claude
5 min read

Lernreise 5/7: Day 3: Fifty Nodes and a Burning Budget

By day three, the main workflow had fifty-two nodes. I want you to sit with that number for a moment. Fifty-two nodes in n8n. Conditional branches, error handlers, HTTP request nodes, code nodes with JavaScript doing things that code nodes in a visual workflow tool were never meant to do. Sub-expressions referencing field names from nodes seventeen steps back. The canvas was a tangle of lines that looked, from a distance, like someone had dropped a bowl of spaghetti on a circuit board and decided to ship it.

lernreise n8n ai debugging
4 min read

Lernreise 4/7: The Grand Plan: RAG, Vectors, and a 7-Cent Bargain

Before touching a single node in n8n, I asked Gemini a sensible question: for this problem, is n8n or Python the better choice? Gemini said n8n, clearly and confidently. It was the right tool for orchestration, it said. Visual workflows, lower barrier, easier to iterate. Perfect for this use case. I want to note this for the record, because it becomes relevant later. The architecture I had in mind had several parts.

lernreise ai rag chromadb mistral n8n paperless-ngx
4 min read

Lernreise 3/7: Teaching a Machine to Build Machines

Before this week, I had never used OpenTofu. I knew it was a Terraform fork, I had seen it mentioned in the same breath as infrastructure as code, and that was roughly where my knowledge ended. Ansible I knew slightly better, in the way that you know a neighbour’s name without having had a proper conversation. I was aware of what it does. I had never sat down and done it.

lernreise ai opentofu ansible proxmox infrastructure-as-code
3 min read

Lernreise 2/7: The Starting Point: A Thousand Untagged Documents

Six months ago I migrated my homelab. The old machine was a netbook that had served faithfully for years, and by the end of its life it was doing things that its manufacturer had never intended and would probably have considered unkind. I replaced it with a MiniPC: an N150 processor, 16 GB of RAM, a form factor that fits in a drawer. It runs Proxmox. It is fast. It is quiet. I am unreasonably pleased with it.

lernreise ai paperless-ngx homelab n8n mistral
3 min read

Lernreise 1/7: Just Do It (The Expensive Way)

There is a particular kind of paralysis that sets in when you follow the AI space professionally. Not ignorance. The opposite. Too much information, too fast, from too many directions at once. I am an IT professional. I have been one for a long time. My day job is coordination, communication, managing third-party software across a range of quality levels that would make a QA engineer weep. I use chatbots daily. I have Copilot set up in VS Code. I understand, broadly, what large language models are doing and why people are excited about them.

lernreise ai homelab learning