Series
AI, in plain words.
For the people who approve AI projects and the people building with AI tools: owners, product managers, team leads, juniors, engineers changing paths. No jargon. What to check, what to ask, and what can go wrong, with a checklist you can use today.
Demo or system? How to tell before you pay, or before you launch
A demo proves an idea can work once; a system keeps working with real data, real users and real mistakes. What a demo hides, the signs of a real system, and the questions to ask before you pay or launch.
Your AI-built app works. Here’s what it’s missing before real users
An app built with AI tools can work well on your screen and still be unsafe for customers. The pieces usually missing, from logins and secrets to backups, cost limits and monitoring, and a prioritized list to work through before launch.
10 questions before you approve, or start, an AI project
Ten plain questions that turn an AI idea into a project with a clear outcome: the number to move, the data, who checks the answers, cost per use, who owns it, and what happens when it fails and after launch.
What an AI feature really costs, and what drives the price
An AI feature has two price tags: building it and running it. What drives each one, from volume and model size to the quality bar, how to estimate the cost of one useful result, and how to set budget alerts before the bill surprises you.
Secrets, keys and data: what you should never paste into a chat
Keep your keys, your customers’ data and your contracts safe while still getting help from AI chats. What should never go in, why it matters, what to do instead, and the steps to take if it already happened.
How to tell whether the AI’s code is good, without being an expert
Six signals anyone can check in an afternoon, plus the questions to ask the AI tool and a reviewer, so you know whether the code your project runs on is ready to trust.
Tests, explained for people who never wrote them
What an automated test is, why it matters more when AI writes the code, which few tests to start with, and how to tell whether the tests an AI tool wrote actually check anything.
Build, buy or wait: deciding where AI belongs in your business
A plain decision guide for leaders: when an off-the-shelf AI tool is the smart move, when building your own pays off, when waiting is the better call, and how to combine them.
AI risks in plain language: what can go wrong, and how to limit it
Six real ways an AI feature goes wrong, from confident wrong answers to surprise bills: what each looks like in practice, and the plain controls that keep each one small.
From prototype to production: the checklist
The grouped checklist that turns a working prototype, often built fast with AI tools, into software customers can rely on: ownership, security, data, quality, operations, costs and people.
Want us to look
at your site?
Tell us where traffic, revenue or your numbers stopped making sense. We will tell you what we would check first.
Prefer to write directly? enable JavaScript to see the address