Notes on building the AI-native web.
Page 3 of 17
Should you hire someone for AIEO or do it yourself?
A meaningful share of the work is unglamorous editing only you can do. Here is the line between what to keep and what to buy.
How to redesign without losing your search traffic
The traffic drop after a relaunch is almost always self-inflicted, and almost always the same four causes.
Where AI fits in an e-commerce business
Product data, support volume and returns are the three places it pays. Recommendation engines are further down the list than you’d think.
Where AI employees fail most often
Six failure patterns, none of them about model capability. Every one is a decision somebody didn’t make.
Multi-tenancy: the decision that shapes everything else
How you separate one customer’s data from another’s determines your security posture, your migrations, and your pricing. Decide it deliberately.
When your provider changes the model underneath you
Behaviour shifts without a release on your side. How to notice, and what to have ready before it happens.
Designing an API other teams can build on
An API is a promise you have to keep for years. The design decisions that make that survivable, made at the start.
How to switch off an AI feature
Not every feature works. Removing one cleanly is a skill, and doing it badly is how a team decides never to try again.
Scaling an AI employee from one workflow to five
The second workflow is not half the work of the first. It’s where you find out whether you built a system or a demo.
How to design a pricing page that doesn’t lose people
The most visited page on most sites, and the one most likely to be built as a wall of comparison. What buyers are actually doing there.
Where the time actually goes in a slow web app
Almost never the language, almost always the database and the network. Measure before optimising anything.
Microcopy: buttons, labels and error messages
The smallest words on the site do the most work, and they’re usually the only ones nobody was assigned to write.