Seven AI app builders, sorted by what you own at the end
Five of these seven builders will hand you the code. Whether it runs anywhere else depends on the database, the logins and the secrets.

Independent · Unsponsored · Receipts included
Tutorials that assume you have a real repo and a deadline. Comparisons scored round by round, with the tasks published so you can rerun them yourself. Nobody pays us for a verdict.
This week
Five of these seven builders will hand you the code. Whether it runs anywhere else depends on the database, the logins and the secrets.

Head to head
We gave both CLI agents the same nine tasks in the same messy repo and scored every round. The gap is not where the marketing says it is.

Two AI-native editors, two philosophies about how much rope to give the model. We used both as a daily driver for a month.

Do it yourself
One PowerShell command installs Claude Code on Windows. Here's the exact fix for every install error: PATH, wrong shell, Git Bash, WSL and more.

A prompt is a suggestion. A hook is a guarantee. Wire up formatting, guardrails and notifications in about twenty minutes.

Model Context Protocol without the spec-reading. One server, three tools, and a working connection to a real client.

The long view
Five of these seven builders will hand you the code. Whether it runs anywhere else depends on the database, the logins and the secrets.

Nine tasks, one deliberately broken repo, and a scoring rule that allows ties. The whole kit is public so you can rerun it and disagree with us.

Checkout was built for humans with thumbs. Here is what changes when the shopper is an agent with an API key and a budget.

The newsletter
We only send when we have actually run the thing. Roughly weekly, sometimes not. Unsubscribe in one click.