A Data Elixir learning cohort

The Agent Course

Learn how to build AI agents for everyday data tasks.

What you'll do: Bring a recurring workflow from your own work, build an agent around it, and learn the patterns for making these systems reliable and extensible.

Who it's for: It's for you if you've written some Python before (even badly, years ago), you can open a terminal, and there's a recurring task that you'd love to stop doing.

How it works: Each week, there will be two, 1-hour live sessions (recordings will be available), a private community for discussion & show-and-tell, and a homework assignment that will build your agent in stages.

The tech we use: You'll learn a pattern we call the directory-as-agent. Your agent is an ordinary folder on your machine: plain text instructions, a few scripts, and the files it works with. No framework, no orchestration platform, no vendor dashboard. You'll need a coding assistant and an API key. If you already write code, you have everything else.

FAQs:

What workflows make good agents for this course?
The sweet spot is a task that repeats, that needs judgment but not much, and where you can tell whether the output is correct.If you could explain the task to a sharp new hire in a page or less, it's a good candidate. The best projects are usually boring ones. That's the point. You want the thing that eats forty-five minutes every Monday, not the most impressive thing you can imagine.If you need some ideas, here are some projects that would make good agents for this course ->

Why a folder instead of a framework?
The directory-as-agent approach offers a few key advantages:1) The agent is completely transparent. Every instruction your agent follows is a file you can open, edit, and diff. When it does something you don't expect, you can find out why by reading a file, not by digging through a vendor's abstraction layer.2) This scheme is also tool-agnostic. Point Claude Code, Codex, Cursor, or whatever ships next quarter at the same folder and it works. The tooling in this space churns constantly but your agent shouldn't have to be rewritten every time it does.3) The agents you build in this course run locally and stay on your machine. Your data, your credentials, and your prompts all live in your own file system and under your own version control. Nothing gets uploaded to a platform you don't control.

What if I can't use my company's data?
You don't need it. Build the course project on synthetic data that mirrors the shape of the real thing, then point the agent at whatever model your company has approved. A local model will work too. Because the agent is just a folder of files, swapping the model is a config change, not a rewrite.

How much time will it take?
Including the 2 live sessions and homework, you should plan for 3-5 hours total each week.

What if I fall behind?
Most people will miss a session somewhere and it's fine. Recordings go up the same day, and the course is built so each week ships something small rather than building one big thing all at once. If you get stuck, there's a Help channel and office hours.

When are the online sessions?
The live sessions will happen on Mondays and Thursdays at 12:00 pm (noon) Eastern Time. That's 9:00 am Pacific and 5:00 pm in London.

How much does it cost?
It's $297, and for this founding cohort, that $297 also counts toward any program I launch later. If your employer has a training budget, here's a request template you can customize for your manager >

I'm Lon. I've published Data Elixir every week since 2015, to more than 45,000 data professionals.Most people don't realize I'm a software engineer, not a data scientist. I started Data Elixir while building tools for the data science team on NASA's MMS mission, mostly as a way to get my head around their world. I kept it going after launch and never stopped.These days I run agents in production on my own business. They help me curate Data Elixir, track trends across the internet, and monitor an investment portfolio. The pattern I teach in this course is the one I use every day, on work I depend on.I also write about engineering and technology at lonriesberg.com