Blog

One unchanged pipeline (load, profile, test, model, explain) run across ten open datasets, with a plain-language read and the full technical report for each.

Serious data analysis stayed out of reach for small businesses because of cost, not need. AI agents change that arithmetic. Here is what it now costs.

Research, write, send, check, recover. An AI agent ran my whole cold-email pipeline using Claude, Resend, and a domain I already owned. Cost: zero.

Running a Recency-Frequency-Monetary breakdown on an open orders dataset, and what it says about where revenue really sits.

The unglamorous corner of India's job market that the big portals forgot, and why AI finally made it worth solving.

Sharing what you learn as you learn it is the cheapest marketing there is, and the only kind that still works when nobody has heard of you yet.

Synchronous, blocking code review is the biggest tax on shipping. Make review asynchronous, and trust the tests.

Why 'one skill per use case' is going to collapse under its own weight, and the three-tier model to build instead.

A room full of people thinking out loud, all at once, is the worst environment for thinking. Write first. Read first. Then meet.