Notes on method, one project at a time.

When we finish a project, we publish a write-up of how we approached it: the problem framing, the methodology, and what we learned, never a client's confidential details.

The first write-ups are on their way.

New pieces go up as work wraps, and each one is written to be useful whether or not you ever hire us. In the meantime, the closest thing we have is the approach behind our existing projects.

Read the project write-ups →

What we'll be writing about

CRISP-DM in practice Topic modeling & LLMs on real text Anomaly detection without labels Forecasting that drives a decision Segmentation that changes what you do Human-first automation Getting models past the demo stage When data science isn't the answer

Want the thinking applied to your problem?

Skip the write-ups and bring us the real thing. First session's free.

Book a free discovery session