There are two stories about AI and code. One is the one everyone talks about: that language models write programs for us. The other is the one that is more important, but that almost no one talks about: that code keeps language models in check.
The two stories are the same story. But you have to tell them together to understand where the field is actually heading.
For a year, I've been writing notes in a system called IWE. It's a small command-line tool that treats markdown files as a graph — notes link to each other, and you can navigate, search, and restructure without directly touching the files. It's my working memory layer as a strategic advisor.
This week, an MCP server was added to it. And it's the first time I've had a real experience of sharing memory with a machine.
On Wednesday, I needed something mundane: a list of board members in a number of Danish companies. Not for a database. Not for a product. Just for an afternoon of lead research — who sits where, and which chairmen overlap with people I'm already talking to.
That kind of data is public. It's on datacvr.virk.dk. Every single company in Denmark has a page. It should take twenty minutes.
There's a difference between working with AI and working practically with AI.
The former is using ChatGPT from a browser. The latter is building something where AI is one step among many—where data needs to be fetched, validated, sent to a model, checked, transformed, and stored elsewhere. Almost all commercial AI work is of the latter kind.
And if you're doing the latter, Nushell should live in your terminal.
I recently wrote about how I automate my blog releases in one command — text in, article with image out. That flow runs in a shell most people have never heard of: Nushell. And it's not a random choice.
When I build what I call compound AI systems — meaning systems where eg. language models and image models are combined with other components to solve a real task — the most important question isn't "which model are we using?". It's "what do we surround the model with?".
And that's where Nushell comes in.
I talk a lot about AI solving real business problems, not just impressing in a demo. So let me show you an example from my own daily life.
Every time I write an article for docujai.com, it has to go through the same chain of small tasks: post the text to Drupal via JSON:API, generate an illustrative image, give the image the right visual expression with my logo in the corner, upload it to the article, set alt-text, patch the relationship between node and file. It doesn't take long to do manually. It takes a long time to do it every time.
There's a conversation I hear repeatedly at companies that want AI to "understand" their knowledge.
It typically starts like this: "We have our procedures, our documents, our emails — but the AI can't find the right information. We need better search."
The solution vendors offer is always technical and always expensive: embeddings, vector databases, RAG pipelines. Words that sound impressive and cost accordingly.
The problem is, the solution is rarely what's missing.
I recently gave a talk to twelve people, the vast majority of whom had no prior knowledge of AI. Several were openly negative and made no secret of it. I agreed with many of their objections — they were based more on intuition than experience, but the intuition wasn't wrong.
When I realized what kind of audience I was facing, I ditched the slides and preparation and improvised for the rest of the time. It turned out to be one of my best talks.
That's not what I want to write about.
Mise, IWE, and Nushell together give me a workflow that works every day.
The biggest productivity problem I know is not a lack of tools. It's the transitions between them.
You know what you need to do. You open the terminal. And then you spend five minutes trying to remember which folder you were in, what happened last, which note was relevant, and what you actually decided on Friday. Before you've even started, you're already a bit tired.
With one command in Nushell, you can view your knowledge base from the outside — and discover things you didn't know you didn't know.
It's all about overview.
I discovered something new today. Not in a note, not in a meeting — but in a terminal window.