Shagility argues that clear, descriptive column names in databases let LLMs understand data better than relying on downstream BI layers to rename them. He shows how Claude can validate a conceptual model against actual data, identify outliers, and quantify process funnels, turning institutional knowledge into stored context that chains data workflows together.
Chapters
Cause what we know is if we point the LLM at a set of data that's physical, that is well named, it does a much better job than if it has to go through another layer. So why do we have these BI semantic layers where, you know, we rename the column into a pretty name? Just fricking make the column a pretty name at the beginning. Now, 20 years ago, we couldn't do that. I remember we, like, what was it? SQL Server? One of them had an 8-character limit on the column name. Yeah, there was always constraints we used to have that we don't. We don't have anymore. And then the feedback loop. So for example, when I go and model something, I work with Claude and I have a guess of what the model, you know, the conceptual model is going to be. It now goes and looks at the actual data and it validates it for me, whether we've got it right or not. It goes, well, we think this is a relationship and now I've gone and looked through the data and actually 80% of the times that is the relationship, but there's 20% where it's not. Or we have a process, a funnel, right? A series of steps., and it goes and says, yeah, actually, you know, this percentage of the data follows those steps, but here's all the outliers. It's doing that work for me. It's giving me that feedback. And that feedback needs to go back into wherever we store the context so that it's now captured, uh, because it used to be in people's heads. So that, that's, you know, one of the things, um, that I'm seeing is, is the ability to kind of daisy chain all these little bits of data work that we used to do separately.
