Making data legible to people who don't love data

Most analyses die in a slide deck. A few change a decision. The difference is almost never the model — it's the translation.

The hardest part of data science isn't the analysis. It's getting someone who doesn't think in distributions to act on one.

Lead with the decision, not the method

Stakeholders don't want your methodology — they want to know what to do. Open with the recommendation and the one number that backs it. The rigor belongs in the appendix, ready when someone pushes, not in the first slide.

One chart, one argument

If a chart needs a paragraph to explain, it's doing two jobs. Split it. Every visual should make exactly one point, and the title should be that point — "Retention recovered after the May release," not "Retention by cohort."

Name the uncertainty out loud

Counterintuitively, stating what you don't know builds trust. "We're confident on direction, less so on magnitude" makes the parts you are sure about more credible.

This is a placeholder article — replace it with your own writing at content/articles/making-data-legible.md.