A person moving through a bright office stairwell
Insights

How this work actually goes

Writing about the parts of AI delivery that decide whether a project works — evaluation, architecture, cost and the reasons pilots stall. Written for the people who have to make the decision and live with it, not for search engines.

An analyst working at a screen of code in a bright office Delivery · 9 min read

Why AI pilots fail (and what production actually requires)

A demo proves an idea is possible. Production proves it is reliable, affordable and owned. Here is the gap between them, itemised.

A long meeting-room table in a quiet modern office
Economics · 11 min read

What actually drives the cost of an AI agent

Build cost, running cost, and the cost nobody budgets for — and why architecture, not model choice, decides all three.

Read
A screen of code under review
Quality · 10 min read

How to evaluate an AI agent before you trust it with customers

Accuracy is not one number. A practical method for building an evaluation suite that catches the failures that matter to your business.

Read

Have a question we haven’t written about?

Ask it directly. We answer technical questions without a sales call attached.

Book a call How we work